Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3531 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.5552. Min Act: -0.1700
Data Index: 2642465 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.5552. Min Act: -0.1700
Data Index: 2110651 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.4927. Min Act: -0.1700
Data Index: 216437 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.4614. Min Act: -0.1700
Data Index: 1300906 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.4614. Min Act: -0.1700
Data Index: 8529846 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.4614. Min Act: -0.1700
Data Index: 8377503 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.4302. Min Act: -0.1700
Data Index: 1475262 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.4302. Min Act: -0.1700
Data Index: 6207087 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.3989. Min Act: -0.1700
Data Index: 3730690 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.3989. Min Act: -0.1699
Data Index: 5318712 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.4302. Min Act: -0.1699
Data Index: 1433049 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.4302. Min Act: -0.1700
Data Index: 6542225 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.3989. Min Act: -0.1700
Data Index: 400190 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.3989. Min Act: -0.1700
Data Index: 6746774 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.3989. Min Act: -0.1700
Data Index: 3477236 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.3989. Min Act: -0.1700
Data Index: 5830376 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.3989. Min Act: -0.1700
Data Index: 6827916 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.3677. Min Act: -0.1700
Data Index: 3229448 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.4302. Min Act: -0.1700
Data Index: 6927814 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5552. Min Range: -5.5552
Max Act: 5.3989. Min Act: -0.1700
Data Index: 6218035 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19