Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5906 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1209. Min Range: -4.1209
Max Act: 4.1209. Min Act: -0.1700
Data Index: 8671714 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1209. Min Range: -4.1209
Max Act: 4.0896. Min Act: -0.1700
Data Index: 8469530 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1209. Min Range: -4.1209
Max Act: 4.0584. Min Act: -0.1700
Data Index: 1129391 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1209. Min Range: -4.1209
Max Act: 4.0271. Min Act: -0.1700
Data Index: 6827740 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.9646. Min Act: -0.1700
Data Index: 7296504 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.9333. Min Act: -0.1700
Data Index: 7296489 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.9021. Min Act: -0.1700
Data Index: 5394773 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.8083. Min Act: -0.1700
Data Index: 7566090 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.8083. Min Act: -0.1700
Data Index: 3894496 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.7770. Min Act: -0.1700
Data Index: 4741352 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.7457. Min Act: -0.1700
Data Index: 2285963 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.7144. Min Act: -0.1700
Data Index: 4967635 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.7144. Min Act: -0.1700
Data Index: 2507226 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.7144. Min Act: -0.1700
Data Index: 4273185 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.6831. Min Act: -0.1700
Data Index: 1364663 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.7144. Min Act: -0.1700
Data Index: 7163614 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.7144. Min Act: -0.1700
Data Index: 2831782 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.6831. Min Act: -0.1700
Data Index: 5612832 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.6831. Min Act: -0.1700
Data Index: 7352440 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1209. Min Range: -4.1209
Max Act: 3.6518. Min Act: -0.1700
Data Index: 7662352 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19