Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1013. Min Range: -7.1013
Max Act: 7.1013. Min Act: -0.1700
Data Index: 6793207 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.9763. Min Act: -0.1700
Data Index: 5341354 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.8826. Min Act: -0.1700
Data Index: 3264377 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.7576. Min Act: -0.1700
Data Index: 8292655 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.7888. Min Act: -0.1700
Data Index: 7649692 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.7263. Min Act: -0.1700
Data Index: 4506593 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.6638. Min Act: -0.1700
Data Index: 8246320 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.6326. Min Act: -0.1700
Data Index: 581525 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.6638. Min Act: -0.1700
Data Index: 1216419 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.5388. Min Act: -0.1700
Data Index: 7443491 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.5076. Min Act: -0.1700
Data Index: 3354663 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.5076. Min Act: -0.1700
Data Index: 4267649 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.5076. Min Act: -0.1700
Data Index: 344505 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.4763. Min Act: -0.1700
Data Index: 3671024 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.4763. Min Act: -0.1700
Data Index: 3242610 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.4763. Min Act: -0.1700
Data Index: 278557 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.4451. Min Act: -0.1700
Data Index: 3753192 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.4451. Min Act: -0.1700
Data Index: 3030223 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.4138. Min Act: -0.1700
Data Index: 2386766 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1013. Min Range: -7.1013
Max Act: 6.4451. Min Act: -0.1700
Data Index: 95863 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19