Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3686 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.3559. Min Act: -0.1700
Data Index: 8194621 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.4184. Min Act: -0.1700
Data Index: 6531446 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.3872. Min Act: -0.1700
Data Index: 3580009 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.3559. Min Act: -0.1700
Data Index: 3346795 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.3559. Min Act: -0.1700
Data Index: 2724414 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.3247. Min Act: -0.1700
Data Index: 5101091 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.2934. Min Act: -0.1700
Data Index: 5988173 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.2309. Min Act: -0.1700
Data Index: 6085652 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.1997. Min Act: -0.1700
Data Index: 4453491 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.1997. Min Act: -0.1700
Data Index: 3824206 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.1997. Min Act: -0.1700
Data Index: 1562435 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.1684. Min Act: -0.1700
Data Index: 2228251 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.1997. Min Act: -0.1700
Data Index: 2829840 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.1997. Min Act: -0.1700
Data Index: 4361971 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.1684. Min Act: -0.1700
Data Index: 8736066 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.1372. Min Act: -0.1700
Data Index: 1203189 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.1059. Min Act: -0.1700
Data Index: 438171 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.1372. Min Act: -0.1700
Data Index: 4048460 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.1372. Min Act: -0.1700
Data Index: 4166029 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4184. Min Range: -5.4184
Max Act: 5.1372. Min Act: -0.1700
Data Index: 6563781 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19