Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1034. Min Range: -5.1034
Max Act: 5.1034. Min Act: -0.1700
Data Index: 8768487 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1034. Min Range: -5.1034
Max Act: 5.0722. Min Act: -0.1700
Data Index: 4220763 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1034. Min Range: -5.1034
Max Act: 5.0409. Min Act: -0.1700
Data Index: 3284860 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.8534. Min Act: -0.1700
Data Index: 3730908 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.8222. Min Act: -0.1700
Data Index: 6667340 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.7909. Min Act: -0.1700
Data Index: 2310 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.7597. Min Act: -0.1700
Data Index: 2451201 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.7284. Min Act: -0.1700
Data Index: 7592915 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.7284. Min Act: -0.1700
Data Index: 3334972 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.6972. Min Act: -0.1700
Data Index: 1040074 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.7284. Min Act: -0.1700
Data Index: 8516008 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.6972. Min Act: -0.1700
Data Index: 1272160 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.6659. Min Act: -0.1700
Data Index: 149669 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.6972. Min Act: -0.1700
Data Index: 6801342 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.6347. Min Act: -0.1700
Data Index: 3787012 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.6659. Min Act: -0.1700
Data Index: 8503207 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.6347. Min Act: -0.1700
Data Index: 2478252 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.5722. Min Act: -0.1700
Data Index: 5529138 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.5722. Min Act: -0.1700
Data Index: 3475092 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1034. Min Range: -5.1034
Max Act: 4.5409. Min Act: -0.1700
Data Index: 3608567 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19