Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4830 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.2327. Min Act: -0.1700
Data Index: 3006346 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.1226. Min Act: -0.1700
Data Index: 4489355 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.1068. Min Act: -0.1700
Data Index: 7829144 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0910. Min Act: -0.1700
Data Index: 5598855 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.1068. Min Act: -0.1700
Data Index: 7231817 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0910. Min Act: -0.1700
Data Index: 3434824 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0910. Min Act: -0.1700
Data Index: 8594160 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0595. Min Act: -0.1700
Data Index: 7743456 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0595. Min Act: -0.1700
Data Index: 7766205 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0595. Min Act: -0.1700
Data Index: 3972380 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0437. Min Act: -0.1700
Data Index: 1180187 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0437. Min Act: -0.1700
Data Index: 6158626 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0279. Min Act: -0.1700
Data Index: 3466374 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0279. Min Act: -0.1700
Data Index: 1152339 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0279. Min Act: -0.1700
Data Index: 8291572 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0437. Min Act: -0.1700
Data Index: 6565774 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0121. Min Act: -0.1700
Data Index: 2954571 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0279. Min Act: -0.1700
Data Index: 8181494 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2327. Min Range: -3.2327
Max Act: 3.0437. Min Act: -0.1700
Data Index: 376493 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2327. Min Range: -3.2327
Max Act: 2.9963. Min Act: -0.1700
Data Index: 4673242 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19