Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2667 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.5743. Min Act: -0.1700
Data Index: 4440383 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.5743. Min Act: -0.1700
Data Index: 7100724 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.5118. Min Act: -0.1700
Data Index: 5942336 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.5118. Min Act: -0.1700
Data Index: 5828051 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.4805. Min Act: -0.1700
Data Index: 5384049 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.4805. Min Act: -0.1700
Data Index: 5845865 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.4493. Min Act: -0.1700
Data Index: 11308 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.4493. Min Act: -0.1700
Data Index: 7145717 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.4493. Min Act: -0.1700
Data Index: 8061035 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.4180. Min Act: -0.1700
Data Index: 6762138 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.4180. Min Act: -0.1700
Data Index: 3627284 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.4180. Min Act: -0.1700
Data Index: 8267532 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.3868. Min Act: -0.1700
Data Index: 8533340 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.3868. Min Act: -0.1700
Data Index: 5240178 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.3868. Min Act: -0.1700
Data Index: 1053382 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.3868. Min Act: -0.1700
Data Index: 3899965 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.3868. Min Act: -0.1700
Data Index: 6741049 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.3868. Min Act: -0.1700
Data Index: 4891100 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.3555. Min Act: -0.1699
Data Index: 6328247 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5743. Min Range: -6.5743
Max Act: 6.3555. Min Act: -0.1700
Data Index: 4349958 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19