Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2102. Min Range: -5.2102
Max Act: 5.2102. Min Act: -0.1700
Data Index: 4061540 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2102. Min Range: -5.2102
Max Act: 5.0852. Min Act: -0.1700
Data Index: 1181891 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.9914. Min Act: -0.1700
Data Index: 6387132 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.9602. Min Act: -0.1700
Data Index: 5833175 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.9602. Min Act: -0.1700
Data Index: 5527028 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.9602. Min Act: -0.1700
Data Index: 136000 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.9289. Min Act: -0.1700
Data Index: 6469159 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.9289. Min Act: -0.1700
Data Index: 4189377 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.9289. Min Act: -0.1700
Data Index: 1463229 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.8977. Min Act: -0.1700
Data Index: 6281888 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.8664. Min Act: -0.1700
Data Index: 1210268 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.8664. Min Act: -0.1700
Data Index: 1463240 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.8352. Min Act: -0.1700
Data Index: 135996 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.8664. Min Act: -0.1700
Data Index: 135999 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.8352. Min Act: -0.1700
Data Index: 5002982 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.8352. Min Act: -0.1700
Data Index: 5818846 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.8039. Min Act: -0.1700
Data Index: 5080020 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.8039. Min Act: -0.1700
Data Index: 4948389 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.8039. Min Act: -0.1700
Data Index: 6281891 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2102. Min Range: -5.2102
Max Act: 4.8352. Min Act: -0.1700
Data Index: 1463234 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19