Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.8180. Min Act: -0.1700
Data Index: 8518394 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.7555. Min Act: -0.1700
Data Index: 74778 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.5367. Min Act: -0.1700
Data Index: 7313765 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.5055. Min Act: -0.1700
Data Index: 4702648 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.5055. Min Act: -0.1700
Data Index: 8141185 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.4430. Min Act: -0.1700
Data Index: 1940090 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.4117. Min Act: -0.1700
Data Index: 4048297 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.4117. Min Act: -0.1700
Data Index: 3677646 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.3805. Min Act: -0.1700
Data Index: 3658655 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.3805. Min Act: -0.1700
Data Index: 3775597 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.3180. Min Act: -0.1700
Data Index: 7838272 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.3492. Min Act: -0.1700
Data Index: 6409418 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.3180. Min Act: -0.1700
Data Index: 8088819 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.2555. Min Act: -0.1700
Data Index: 4032070 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.2555. Min Act: -0.1700
Data Index: 3495668 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.2555. Min Act: -0.1700
Data Index: 6428122 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.1930. Min Act: -0.1700
Data Index: 3729151 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.2242. Min Act: -0.1700
Data Index: 2518600 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.1930. Min Act: -0.1700
Data Index: 7481843 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8180. Min Range: -7.8180
Max Act: 7.1930. Min Act: -0.1700
Data Index: 283419 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19