Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1929. Min Range: -5.1929
Max Act: 5.1929. Min Act: -0.1700
Data Index: 173006 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1929. Min Range: -5.1929
Max Act: 5.1304. Min Act: -0.1700
Data Index: 2279697 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1929. Min Range: -5.1929
Max Act: 5.0992. Min Act: -0.1700
Data Index: 1521839 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1929. Min Range: -5.1929
Max Act: 5.0679. Min Act: -0.1700
Data Index: 683470 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1929. Min Range: -5.1929
Max Act: 5.0679. Min Act: -0.1700
Data Index: 4518007 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.9117. Min Act: -0.1700
Data Index: 270478 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.9117. Min Act: -0.1700
Data Index: 106625 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.8492. Min Act: -0.1700
Data Index: 3240800 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.8179. Min Act: -0.1700
Data Index: 1885037 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.7867. Min Act: -0.1700
Data Index: 4633099 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.7867. Min Act: -0.1700
Data Index: 5903885 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.7554. Min Act: -0.1700
Data Index: 464226 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.7554. Min Act: -0.1700
Data Index: 4345493 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.6929. Min Act: -0.1700
Data Index: 3713742 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.6929. Min Act: -0.1700
Data Index: 7299343 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.6929. Min Act: -0.1700
Data Index: 366337 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.6929. Min Act: -0.1700
Data Index: 7299354 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.6929. Min Act: -0.1700
Data Index: 952425 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.7242. Min Act: -0.1700
Data Index: 8661919 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1929. Min Range: -5.1929
Max Act: 4.6929. Min Act: -0.1700
Data Index: 8717144 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19