Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0664. Min Range: -8.0664
Max Act: 8.0664. Min Act: -0.1700
Data Index: 5492478 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.5664. Min Act: -0.1700
Data Index: 318585 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.5039. Min Act: -0.1700
Data Index: 3694777 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.3164. Min Act: -0.1700
Data Index: 169293 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.2852. Min Act: -0.1700
Data Index: 575105 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.1289. Min Act: -0.1700
Data Index: 318588 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.1602. Min Act: -0.1700
Data Index: 5008167 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.1602. Min Act: -0.1700
Data Index: 403258 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.1289. Min Act: -0.1700
Data Index: 993827 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.1289. Min Act: -0.1700
Data Index: 7083655 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.0977. Min Act: -0.1700
Data Index: 4085327 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.0664. Min Act: -0.1700
Data Index: 709827 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.0664. Min Act: -0.1700
Data Index: 1242944 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.0352. Min Act: -0.1700
Data Index: 4710958 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.0352. Min Act: -0.1700
Data Index: 574032 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.0039. Min Act: -0.1700
Data Index: 8748359 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0664. Min Range: -8.0664
Max Act: 6.9414. Min Act: -0.1700
Data Index: 8248893 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0664. Min Range: -8.0664
Max Act: 6.9414. Min Act: -0.1700
Data Index: 8623150 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0664. Min Range: -8.0664
Max Act: 6.9414. Min Act: -0.1700
Data Index: 3783585 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0664. Min Range: -8.0664
Max Act: 6.9414. Min Act: -0.1700
Data Index: 2286972 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19