Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 67 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.6148. Min Act: -0.1700
Data Index: 5363519 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.6148. Min Act: -0.1700
Data Index: 3757894 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.5835. Min Act: -0.1700
Data Index: 392559 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.6148. Min Act: -0.1700
Data Index: 5408231 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.6148. Min Act: -0.1700
Data Index: 4364480 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.5210. Min Act: -0.1700
Data Index: 853374 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.5210. Min Act: -0.1700
Data Index: 8685317 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.5210. Min Act: -0.1700
Data Index: 7531780 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.5210. Min Act: -0.1700
Data Index: 4963027 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.5210. Min Act: -0.1700
Data Index: 3866565 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.4898. Min Act: -0.1700
Data Index: 3793814 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.4585. Min Act: -0.1700
Data Index: 7150372 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.5210. Min Act: -0.1700
Data Index: 669066 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.4898. Min Act: -0.1700
Data Index: 1892420 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.4585. Min Act: -0.1700
Data Index: 2587428 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.4898. Min Act: -0.1700
Data Index: 1090292 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.4585. Min Act: -0.1700
Data Index: 5814055 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.4273. Min Act: -0.1700
Data Index: 3769166 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.4273. Min Act: -0.1700
Data Index: 1094388 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6148. Min Range: -4.6148
Max Act: 4.4273. Min Act: -0.1700
Data Index: 3213969 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19