Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 515 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.3914. Min Act: -0.1700
Data Index: 7088892 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.3914. Min Act: -0.1700
Data Index: 6563533 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.3914. Min Act: -0.1700
Data Index: 8325628 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.4226. Min Act: -0.1700
Data Index: 1328876 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.3601. Min Act: -0.1700
Data Index: 3494596 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.2976. Min Act: -0.1700
Data Index: 4168367 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.2976. Min Act: -0.1700
Data Index: 7538201 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.2664. Min Act: -0.1700
Data Index: 5919803 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.2664. Min Act: -0.1700
Data Index: 7836297 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.2351. Min Act: -0.1700
Data Index: 7589464 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.2351. Min Act: -0.1700
Data Index: 7363611 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.1726. Min Act: -0.1700
Data Index: 3091530 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.2039. Min Act: -0.1700
Data Index: 5421773 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.2039. Min Act: -0.1700
Data Index: 2346210 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.1414. Min Act: -0.1700
Data Index: 1130836 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.1726. Min Act: -0.1700
Data Index: 5323348 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.1726. Min Act: -0.1700
Data Index: 3248202 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.1726. Min Act: -0.1700
Data Index: 5605051 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.1726. Min Act: -0.1700
Data Index: 3412570 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.1726. Min Act: -0.1700
Data Index: 7828264 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19