Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3989 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1164. Min Range: -10.1164
Max Act: 10.0539. Min Act: -0.1700
Data Index: 4440704 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1164. Min Range: -10.1164
Max Act: 10.1164. Min Act: -0.1700
Data Index: 893825 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.9914. Min Act: -0.1700
Data Index: 5351150 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.8664. Min Act: -0.1700
Data Index: 2201789 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.8664. Min Act: -0.1700
Data Index: 3619948 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.6789. Min Act: -0.1700
Data Index: 6816633 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.6164. Min Act: -0.1700
Data Index: 5997956 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.4914. Min Act: -0.1700
Data Index: 4154486 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.4289. Min Act: -0.1700
Data Index: 7317328 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.4289. Min Act: -0.1700
Data Index: 7419761 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.3664. Min Act: -0.1700
Data Index: 6040680 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.4289. Min Act: -0.1700
Data Index: 7162558 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.3664. Min Act: -0.1700
Data Index: 7639002 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.3664. Min Act: -0.1700
Data Index: 760295 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.3039. Min Act: -0.1700
Data Index: 2124601 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.3039. Min Act: -0.1700
Data Index: 4286603 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.3039. Min Act: -0.1700
Data Index: 1624725 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.3039. Min Act: -0.1700
Data Index: 3212068 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.3039. Min Act: -0.1700
Data Index: 258208 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1164. Min Range: -10.1164
Max Act: 9.3039. Min Act: -0.1700
Data Index: 1319523 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19