Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2135 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.6772. Min Act: -0.1700
Data Index: 412765 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.5647. Min Act: -0.1700
Data Index: 128112 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.5486. Min Act: -0.1700
Data Index: 390634 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.5001. Min Act: -0.1700
Data Index: 1212968 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4676. Min Act: -0.1700
Data Index: 7830411 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4514. Min Act: -0.1700
Data Index: 7600258 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4676. Min Act: -0.1700
Data Index: 8385055 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4351. Min Act: -0.1700
Data Index: 3122145 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4351. Min Act: -0.1700
Data Index: 8570344 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4351. Min Act: -0.1700
Data Index: 2732366 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4676. Min Act: -0.1700
Data Index: 2737410 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4514. Min Act: -0.1700
Data Index: 1661010 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4351. Min Act: -0.1700
Data Index: 6229100 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4351. Min Act: -0.1700
Data Index: 8590453 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4188. Min Act: -0.1700
Data Index: 7856832 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4188. Min Act: -0.1700
Data Index: 4802656 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4188. Min Act: -0.1700
Data Index: 4853971 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4188. Min Act: -0.1700
Data Index: 3626164 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4025. Min Act: -0.1700
Data Index: 7467589 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6772. Min Range: -2.6772
Max Act: 2.4025. Min Act: -0.1700
Data Index: 6770402 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19