Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2198 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.7149. Min Act: -0.1700
Data Index: 6174356 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.6211. Min Act: -0.1700
Data Index: 8640383 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.5899. Min Act: -0.1700
Data Index: 7886808 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.5586. Min Act: -0.1700
Data Index: 2739999 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.5274. Min Act: -0.1700
Data Index: 7961855 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.5274. Min Act: -0.1700
Data Index: 5514270 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.4649. Min Act: -0.1700
Data Index: 3444780 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.4336. Min Act: -0.1700
Data Index: 1546278 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.4336. Min Act: -0.1700
Data Index: 7010223 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.3711. Min Act: -0.1700
Data Index: 517265 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.3711. Min Act: -0.1700
Data Index: 2530180 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.4024. Min Act: -0.1700
Data Index: 4283310 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.3086. Min Act: -0.1700
Data Index: 4824962 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.3086. Min Act: -0.1700
Data Index: 7334703 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.3086. Min Act: -0.1700
Data Index: 626251 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.2774. Min Act: -0.1700
Data Index: 1295777 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.2774. Min Act: -0.1700
Data Index: 2721667 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.2774. Min Act: -0.1700
Data Index: 6907731 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.3086. Min Act: -0.1700
Data Index: 7363896 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7149. Min Range: -6.7149
Max Act: 6.2461. Min Act: -0.1700
Data Index: 8565718 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19