Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3336 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0543. Min Range: -4.0543
Max Act: 4.0543. Min Act: -0.1700
Data Index: 334209 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0543. Min Range: -4.0543
Max Act: 4.0543. Min Act: -0.1700
Data Index: 7966617 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.9918. Min Act: -0.1700
Data Index: 5866386 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0543. Min Range: -4.0543
Max Act: 4.0074. Min Act: -0.1700
Data Index: 2479087 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.9761. Min Act: -0.1700
Data Index: 7524335 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.9761. Min Act: -0.1700
Data Index: 225468 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.9292. Min Act: -0.1700
Data Index: 3284876 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.9136. Min Act: -0.1700
Data Index: 3641956 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.8980. Min Act: -0.1700
Data Index: 7606653 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.8823. Min Act: -0.1700
Data Index: 4769018 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.8823. Min Act: -0.1700
Data Index: 8328999 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.8667. Min Act: -0.1700
Data Index: 1295952 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.8667. Min Act: -0.1700
Data Index: 4417071 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.8823. Min Act: -0.1700
Data Index: 1409655 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.8667. Min Act: -0.1700
Data Index: 4784971 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.8667. Min Act: -0.1700
Data Index: 4249571 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.8823. Min Act: -0.1700
Data Index: 5629207 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.8823. Min Act: -0.1700
Data Index: 449976 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.8511. Min Act: -0.1700
Data Index: 4557459 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0543. Min Range: -4.0543
Max Act: 3.8354. Min Act: -0.1700
Data Index: 8778153 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19