Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1458 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 17.1273. Min Range: -17.1273
Max Act: 17.1273. Min Act: -0.1700
Data Index: 1643622 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.1273. Min Range: -17.1273
Max Act: 16.8773. Min Act: -0.1700
Data Index: 6965287 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.1273. Min Range: -17.1273
Max Act: 16.7523. Min Act: -0.1700
Data Index: 8325177 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.1273. Min Range: -17.1273
Max Act: 16.5648. Min Act: -0.1700
Data Index: 3069767 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.1273. Min Range: -17.1273
Max Act: 16.4398. Min Act: -0.1700
Data Index: 6942550 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.1273. Min Range: -17.1273
Max Act: 16.5023. Min Act: -0.1700
Data Index: 5696399 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.1273. Min Range: -17.1273
Max Act: 16.4398. Min Act: -0.1700
Data Index: 1198737 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.1273. Min Range: -17.1273
Max Act: 16.3148. Min Act: -0.1700
Data Index: 4871852 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.1273. Min Range: -17.1273
Max Act: 16.2523. Min Act: -0.1700
Data Index: 2561104 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.1273. Min Range: -17.1273
Max Act: 16.2523. Min Act: -0.1700
Data Index: 4292628 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.1273. Min Range: -17.1273
Max Act: 16.1273. Min Act: -0.1700
Data Index: 7618126 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.1273. Min Range: -17.1273
Max Act: 16.0023. Min Act: -0.1700
Data Index: 4395829 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.1273. Min Range: -17.1273
Max Act: 16.0023. Min Act: -0.1700
Data Index: 3684826 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.1273. Min Range: -17.1273
Max Act: 15.9398. Min Act: -0.1700
Data Index: 7669910 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.1273. Min Range: -17.1273
Max Act: 15.8773. Min Act: -0.1700
Data Index: 8082236 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.1273. Min Range: -17.1273
Max Act: 15.8773. Min Act: -0.1700
Data Index: 6154944 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.1273. Min Range: -17.1273
Max Act: 15.8773. Min Act: -0.1700
Data Index: 719624 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.1273. Min Range: -17.1273
Max Act: 15.9398. Min Act: -0.1700
Data Index: 4014133 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.1273. Min Range: -17.1273
Max Act: 15.8773. Min Act: -0.1700
Data Index: 518323 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.1273. Min Range: -17.1273
Max Act: 15.7523. Min Act: -0.1700
Data Index: 4862307 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19