Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5090 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.7996. Min Act: -0.1700
Data Index: 8101849 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.7370. Min Act: -0.1700
Data Index: 1983201 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.7057. Min Act: -0.1700
Data Index: 1807521 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.7057. Min Act: -0.1700
Data Index: 8204418 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.6745. Min Act: -0.1700
Data Index: 355340 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.6745. Min Act: -0.1700
Data Index: 3133640 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.6745. Min Act: -0.1700
Data Index: 1221940 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.6432. Min Act: -0.1700
Data Index: 1311963 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.6432. Min Act: -0.1700
Data Index: 8056102 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.6432. Min Act: -0.1700
Data Index: 7687981 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.6432. Min Act: -0.1700
Data Index: 7419176 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.6119. Min Act: -0.1700
Data Index: 1472709 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.6119. Min Act: -0.1700
Data Index: 8056101 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.5806. Min Act: -0.1700
Data Index: 5677101 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.5806. Min Act: -0.1700
Data Index: 6382734 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.5179. Min Act: -0.1700
Data Index: 1930057 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.5179. Min Act: -0.1700
Data Index: 6715937 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.5493. Min Act: -0.1700
Data Index: 942561 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.5493. Min Act: -0.1700
Data Index: 3003317 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7996. Min Range: -3.7996
Max Act: 3.5493. Min Act: -0.1700
Data Index: 4606995 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19