Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3235 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.5512. Min Act: -0.1700
Data Index: 8003479 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.5512. Min Act: -0.1700
Data Index: 8346531 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.5199. Min Act: -0.1700
Data Index: 8193318 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.4574. Min Act: -0.1700
Data Index: 7271967 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.4887. Min Act: -0.1700
Data Index: 6342093 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.4887. Min Act: -0.1700
Data Index: 8003478 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.4887. Min Act: -0.1700
Data Index: 8749979 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.4887. Min Act: -0.1700
Data Index: 2501321 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.4574. Min Act: -0.1700
Data Index: 3106190 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.4574. Min Act: -0.1700
Data Index: 4515377 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.4574. Min Act: -0.1700
Data Index: 2147450 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.4574. Min Act: -0.1700
Data Index: 7876248 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.4262. Min Act: -0.1700
Data Index: 3651415 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.4262. Min Act: -0.1700
Data Index: 5116767 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.3949. Min Act: -0.1700
Data Index: 6105812 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.4262. Min Act: -0.1700
Data Index: 5988266 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.3949. Min Act: -0.1700
Data Index: 5366701 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.3637. Min Act: -0.1700
Data Index: 304827 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.3637. Min Act: -0.1700
Data Index: 7772143 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5512. Min Range: -4.5512
Max Act: 4.3949. Min Act: -0.1700
Data Index: 7776103 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19