Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.9161. Min Act: -0.1700
Data Index: 7035829 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.8848. Min Act: -0.1700
Data Index: 8700996 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.8848. Min Act: -0.1700
Data Index: 4551878 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.9161. Min Act: -0.1700
Data Index: 6379408 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.8535. Min Act: -0.1700
Data Index: 5262662 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.8223. Min Act: -0.1700
Data Index: 4049726 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.7910. Min Act: -0.1700
Data Index: 5070899 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.7284. Min Act: -0.1700
Data Index: 4608282 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.7910. Min Act: -0.1700
Data Index: 3666756 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.7910. Min Act: -0.1700
Data Index: 8070744 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.7910. Min Act: -0.1700
Data Index: 4026380 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.7910. Min Act: -0.1700
Data Index: 3998878 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.7910. Min Act: -0.1700
Data Index: 5171882 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.8223. Min Act: -0.1700
Data Index: 468416 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.7910. Min Act: -0.1700
Data Index: 4798913 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.7597. Min Act: -0.1700
Data Index: 1018087 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.7597. Min Act: -0.1700
Data Index: 1100703 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.7597. Min Act: -0.1700
Data Index: 2099510 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.7597. Min Act: -0.1700
Data Index: 1380990 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9161. Min Range: -3.9161
Max Act: 3.7284. Min Act: -0.1700
Data Index: 3327866 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19