Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4999 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3220. Min Range: -6.3220
Max Act: 6.3220. Min Act: -0.1700
Data Index: 4523745 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3220. Min Range: -6.3220
Max Act: 6.2283. Min Act: -0.1700
Data Index: 4118204 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3220. Min Range: -6.3220
Max Act: 6.1970. Min Act: -0.1700
Data Index: 6003884 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3220. Min Range: -6.3220
Max Act: 6.2283. Min Act: -0.1700
Data Index: 8709850 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3220. Min Range: -6.3220
Max Act: 6.0408. Min Act: -0.1700
Data Index: 2392126 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3220. Min Range: -6.3220
Max Act: 6.0408. Min Act: -0.1700
Data Index: 7254099 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3220. Min Range: -6.3220
Max Act: 6.0720. Min Act: -0.1700
Data Index: 1257052 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3220. Min Range: -6.3220
Max Act: 6.0408. Min Act: -0.1700
Data Index: 3997376 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3220. Min Range: -6.3220
Max Act: 5.9783. Min Act: -0.1700
Data Index: 1027546 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3220. Min Range: -6.3220
Max Act: 6.0095. Min Act: -0.1700
Data Index: 562243 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3220. Min Range: -6.3220
Max Act: 5.9470. Min Act: -0.1700
Data Index: 7655586 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3220. Min Range: -6.3220
Max Act: 5.9470. Min Act: -0.1700
Data Index: 3904686 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3220. Min Range: -6.3220
Max Act: 5.9158. Min Act: -0.1700
Data Index: 161160 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3220. Min Range: -6.3220
Max Act: 5.8845. Min Act: -0.1700
Data Index: 5881610 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3220. Min Range: -6.3220
Max Act: 5.9158. Min Act: -0.1700
Data Index: 2284214 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3220. Min Range: -6.3220
Max Act: 5.8845. Min Act: -0.1700
Data Index: 3061105 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3220. Min Range: -6.3220
Max Act: 5.8533. Min Act: -0.1700
Data Index: 953281 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3220. Min Range: -6.3220
Max Act: 5.8533. Min Act: -0.1700
Data Index: 6447307 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3220. Min Range: -6.3220
Max Act: 5.8220. Min Act: -0.1700
Data Index: 48058 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3220. Min Range: -6.3220
Max Act: 5.8220. Min Act: -0.1700
Data Index: 845817 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19