Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6027 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.7293. Min Act: -0.1700
Data Index: 7666892 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6966. Min Act: -0.1700
Data Index: 2585833 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6722. Min Act: -0.1696
Data Index: 6550772 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6884. Min Act: -0.1699
Data Index: 7252964 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6641. Min Act: -0.1700
Data Index: 7322229 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6722. Min Act: -0.1700
Data Index: 3401330 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6480. Min Act: -0.1680
Data Index: 4476335 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6561. Min Act: -0.1700
Data Index: 7208574 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6321. Min Act: -0.1700
Data Index: 2723548 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6241. Min Act: -0.1700
Data Index: 7682325 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6241. Min Act: -0.1700
Data Index: 5269737 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6162. Min Act: -0.1697
Data Index: 1783664 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6162. Min Act: -0.1700
Data Index: 6064159 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6162. Min Act: -0.1700
Data Index: 1422931 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6083. Min Act: -0.1700
Data Index: 758531 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6162. Min Act: -0.1700
Data Index: 5818568 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6241. Min Act: -0.1700
Data Index: 3508718 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6083. Min Act: -0.1700
Data Index: 2884890 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6004. Min Act: -0.1692
Data Index: 8269937 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7293. Min Range: -0.7293
Max Act: 0.6004. Min Act: -0.1699
Data Index: 645491 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19