Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5106 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1247. Min Range: -6.1247
Max Act: 6.1247. Min Act: -0.1700
Data Index: 2322920 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1247. Min Range: -6.1247
Max Act: 6.0934. Min Act: -0.1700
Data Index: 8563134 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1247. Min Range: -6.1247
Max Act: 6.0309. Min Act: -0.1700
Data Index: 7865702 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.9684. Min Act: -0.1700
Data Index: 6798422 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.9372. Min Act: -0.1700
Data Index: 4462701 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.9059. Min Act: -0.1700
Data Index: 4539475 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.9059. Min Act: -0.1700
Data Index: 287327 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.8747. Min Act: -0.1700
Data Index: 3378122 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.8434. Min Act: -0.1700
Data Index: 1185316 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.8434. Min Act: -0.1700
Data Index: 1867574 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.8122. Min Act: -0.1700
Data Index: 2322921 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.8122. Min Act: -0.1700
Data Index: 2959788 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7809. Min Act: -0.1700
Data Index: 8820802 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7809. Min Act: -0.1700
Data Index: 287994 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7497. Min Act: -0.1700
Data Index: 99008 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7497. Min Act: -0.1700
Data Index: 4462713 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7184. Min Act: -0.1700
Data Index: 215938 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.6872. Min Act: -0.1700
Data Index: 764491 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.6559. Min Act: -0.1700
Data Index: 1867586 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.6559. Min Act: -0.1700
Data Index: 3235883 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19