Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.9049. Min Act: -0.1700
Data Index: 7775267 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.9049. Min Act: -0.1700
Data Index: 2857014 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.8424. Min Act: -0.1700
Data Index: 8120821 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.9049. Min Act: -0.1700
Data Index: 4657344 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.7174. Min Act: -0.1700
Data Index: 5505342 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.7174. Min Act: -0.1700
Data Index: 3146647 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.7174. Min Act: -0.1700
Data Index: 3601803 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.6549. Min Act: -0.1700
Data Index: 8778748 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.5924. Min Act: -0.1700
Data Index: 2965302 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.5924. Min Act: -0.1700
Data Index: 7475693 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.6549. Min Act: -0.1700
Data Index: 6194349 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.5924. Min Act: -0.1700
Data Index: 2940388 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.5299. Min Act: -0.1700
Data Index: 4972597 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.5299. Min Act: -0.1700
Data Index: 8328073 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.4674. Min Act: -0.1700
Data Index: 2891464 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.4674. Min Act: -0.1700
Data Index: 6291340 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.5299. Min Act: -0.1700
Data Index: 426043 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.5299. Min Act: -0.1700
Data Index: 588414 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.4049. Min Act: -0.1700
Data Index: 4353971 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9049. Min Range: -8.9049
Max Act: 8.4049. Min Act: -0.1700
Data Index: 933711 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19