Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 578 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.9551. Min Act: -0.1700
Data Index: 8417956 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.6113. Min Act: -0.1700
Data Index: 350156 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.6113. Min Act: -0.1700
Data Index: 558795 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.5801. Min Act: -0.1700
Data Index: 3034256 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.5488. Min Act: -0.1700
Data Index: 6186281 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.5488. Min Act: -0.1700
Data Index: 8417975 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.4863. Min Act: -0.1700
Data Index: 3727114 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.4238. Min Act: -0.1700
Data Index: 1923632 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.3613. Min Act: -0.1700
Data Index: 8417963 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.3926. Min Act: -0.1700
Data Index: 3564463 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.3613. Min Act: -0.1700
Data Index: 7128883 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.3613. Min Act: -0.1700
Data Index: 6129563 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.3301. Min Act: -0.1700
Data Index: 1544353 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.3301. Min Act: -0.1700
Data Index: 2631184 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.2676. Min Act: -0.1700
Data Index: 8417957 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.2363. Min Act: -0.1700
Data Index: 8476122 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.2051. Min Act: -0.1700
Data Index: 1624112 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.1738. Min Act: -0.1700
Data Index: 3138938 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.1113. Min Act: -0.1700
Data Index: 2527838 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9551. Min Range: -6.9551
Max Act: 6.1426. Min Act: -0.1700
Data Index: 8476121 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19