Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.9443. Min Act: -0.1700
Data Index: 346832 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.8974. Min Act: -0.1700
Data Index: 4643259 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.8974. Min Act: -0.1700
Data Index: 1212468 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.8192. Min Act: -0.1700
Data Index: 967653 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.8349. Min Act: -0.1700
Data Index: 1675204 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.8192. Min Act: -0.1700
Data Index: 2506100 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.8036. Min Act: -0.1700
Data Index: 184870 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.8036. Min Act: -0.1700
Data Index: 2974879 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.8036. Min Act: -0.1700
Data Index: 1947510 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.8036. Min Act: -0.1700
Data Index: 6428197 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.7880. Min Act: -0.1700
Data Index: 636997 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.7880. Min Act: -0.1700
Data Index: 4434094 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.7880. Min Act: -0.1700
Data Index: 4907077 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.7723. Min Act: -0.1700
Data Index: 2127943 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.8036. Min Act: -0.1700
Data Index: 336902 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.7723. Min Act: -0.1700
Data Index: 2341254 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.7880. Min Act: -0.1700
Data Index: 2566792 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.7567. Min Act: -0.1700
Data Index: 8261302 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.7567. Min Act: -0.1700
Data Index: 3547731 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9443. Min Range: -3.9443
Max Act: 3.7411. Min Act: -0.1700
Data Index: 8254307 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19