Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 989 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2563. Min Range: -8.2563
Max Act: 8.2563. Min Act: -0.1700
Data Index: 4138159 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2563. Min Range: -8.2563
Max Act: 8.1313. Min Act: -0.1700
Data Index: 3311434 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.8813. Min Act: -0.1700
Data Index: 2880104 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.8813. Min Act: -0.1700
Data Index: 926149 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.8813. Min Act: -0.1700
Data Index: 2668748 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.5376. Min Act: -0.1700
Data Index: 2474542 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.5376. Min Act: -0.1700
Data Index: 2668743 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.5376. Min Act: -0.1700
Data Index: 7973765 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.3501. Min Act: -0.1700
Data Index: 1799210 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.3501. Min Act: -0.1700
Data Index: 6645913 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.2563. Min Act: -0.1700
Data Index: 1379986 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.2563. Min Act: -0.1700
Data Index: 7608539 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.2251. Min Act: -0.1700
Data Index: 6035188 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.2251. Min Act: -0.1700
Data Index: 3190363 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.1938. Min Act: -0.1700
Data Index: 3317240 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.1626. Min Act: -0.1700
Data Index: 4662350 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.2251. Min Act: -0.1700
Data Index: 946245 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.1938. Min Act: -0.1700
Data Index: 701219 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.1626. Min Act: -0.1700
Data Index: 1085944 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2563. Min Range: -8.2563
Max Act: 7.1626. Min Act: -0.1700
Data Index: 3311433 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19