Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1070 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.6960. Min Act: -0.1700
Data Index: 619853 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.6647. Min Act: -0.1700
Data Index: 5260041 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.6647. Min Act: -0.1700
Data Index: 878998 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.6335. Min Act: -0.1700
Data Index: 8757394 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.6335. Min Act: -0.1700
Data Index: 2339013 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.6022. Min Act: -0.1700
Data Index: 6094941 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.6022. Min Act: -0.1700
Data Index: 1292074 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.5710. Min Act: -0.1700
Data Index: 7897427 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.5397. Min Act: -0.1700
Data Index: 7421184 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.5397. Min Act: -0.1700
Data Index: 1116272 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.5397. Min Act: -0.1700
Data Index: 2048467 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.5397. Min Act: -0.1700
Data Index: 3934940 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.5085. Min Act: -0.1700
Data Index: 7813281 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.5085. Min Act: -0.1700
Data Index: 4525226 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.5085. Min Act: -0.1700
Data Index: 2656296 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.5085. Min Act: -0.1700
Data Index: 2062327 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.4772. Min Act: -0.1700
Data Index: 3374521 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.4772. Min Act: -0.1700
Data Index: 726306 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.4460. Min Act: -0.1700
Data Index: 4592836 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6960. Min Range: -4.6960
Max Act: 4.4772. Min Act: -0.1700
Data Index: 4898574 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19