Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2796 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.8118. Min Act: -0.1700
Data Index: 82875 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.7493. Min Act: -0.1700
Data Index: 931421 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.7181. Min Act: -0.1700
Data Index: 8821765 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.7181. Min Act: -0.1700
Data Index: 3405438 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.4681. Min Act: -0.1700
Data Index: 533971 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.4368. Min Act: -0.1700
Data Index: 8452156 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.4368. Min Act: -0.1700
Data Index: 459414 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.3743. Min Act: -0.1700
Data Index: 8265873 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.3743. Min Act: -0.1700
Data Index: 3473028 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.3431. Min Act: -0.1700
Data Index: 5520415 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.3431. Min Act: -0.1700
Data Index: 3465489 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.3431. Min Act: -0.1700
Data Index: 3869832 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.3118. Min Act: -0.1700
Data Index: 2395652 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.2806. Min Act: -0.1700
Data Index: 5250886 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.2806. Min Act: -0.1700
Data Index: 4930385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.3118. Min Act: -0.1700
Data Index: 792651 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.3118. Min Act: -0.1700
Data Index: 2916085 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.3118. Min Act: -0.1700
Data Index: 2751526 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.2493. Min Act: -0.1700
Data Index: 4130111 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8118. Min Range: -6.8118
Max Act: 6.2806. Min Act: -0.1700
Data Index: 862495 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19