Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2072 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4524. Min Range: -11.4524
Max Act: 11.4524. Min Act: -0.1700
Data Index: 5209661 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4524. Min Range: -11.4524
Max Act: 11.3899. Min Act: -0.1700
Data Index: 2612238 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4524. Min Range: -11.4524
Max Act: 11.3274. Min Act: -0.1700
Data Index: 5209659 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4524. Min Range: -11.4524
Max Act: 11.2649. Min Act: -0.1700
Data Index: 5209658 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4524. Min Range: -11.4524
Max Act: 11.2649. Min Act: -0.1700
Data Index: 5209657 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4524. Min Range: -11.4524
Max Act: 11.1399. Min Act: -0.1700
Data Index: 1687877 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4524. Min Range: -11.4524
Max Act: 11.0774. Min Act: -0.1700
Data Index: 7819247 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4524. Min Range: -11.4524
Max Act: 11.0774. Min Act: -0.1700
Data Index: 5209660 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4524. Min Range: -11.4524
Max Act: 11.0774. Min Act: -0.1700
Data Index: 1801199 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4524. Min Range: -11.4524
Max Act: 11.0149. Min Act: -0.1700
Data Index: 3404283 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4524. Min Range: -11.4524
Max Act: 10.9524. Min Act: -0.1700
Data Index: 194395 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4524. Min Range: -11.4524
Max Act: 10.9524. Min Act: -0.1700
Data Index: 3991979 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4524. Min Range: -11.4524
Max Act: 10.8274. Min Act: -0.1700
Data Index: 1446285 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4524. Min Range: -11.4524
Max Act: 10.8899. Min Act: -0.1700
Data Index: 6834236 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4524. Min Range: -11.4524
Max Act: 10.8274. Min Act: -0.1700
Data Index: 684864 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4524. Min Range: -11.4524
Max Act: 10.8899. Min Act: -0.1700
Data Index: 8323104 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4524. Min Range: -11.4524
Max Act: 10.8274. Min Act: -0.1700
Data Index: 156510 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4524. Min Range: -11.4524
Max Act: 10.7649. Min Act: -0.1700
Data Index: 5132171 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4524. Min Range: -11.4524
Max Act: 10.8274. Min Act: -0.1700
Data Index: 1048283 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4524. Min Range: -11.4524
Max Act: 10.7649. Min Act: -0.1700
Data Index: 1210393 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19