Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1147 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.8005. Min Act: -0.1700
Data Index: 7535374 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.7692. Min Act: -0.1578
Data Index: 6506837 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6755. Min Act: -0.1700
Data Index: 2909552 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6755. Min Act: -0.1699
Data Index: 8084163 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6442. Min Act: -0.1685
Data Index: 964345 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6442. Min Act: -0.1700
Data Index: 8119296 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6442. Min Act: -0.1564
Data Index: 4073339 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6442. Min Act: -0.1700
Data Index: 7395498 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6442. Min Act: -0.1700
Data Index: 1645907 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6442. Min Act: -0.1700
Data Index: 2806110 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6442. Min Act: -0.1697
Data Index: 7605952 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6130. Min Act: -0.1698
Data Index: 1828415 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6442. Min Act: -0.1700
Data Index: 7594645 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6442. Min Act: -0.1697
Data Index: 7584662 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6130. Min Act: -0.1699
Data Index: 1065367 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6130. Min Act: -0.1700
Data Index: 7732322 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6442. Min Act: -0.1700
Data Index: 6994352 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6130. Min Act: -0.1700
Data Index: 6099122 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6130. Min Act: -0.1697
Data Index: 3734192 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8005. Min Range: -7.8005
Max Act: 7.6130. Min Act: -0.1700
Data Index: 4844714 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19