Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1260 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.9106. Min Act: -0.1700
Data Index: 325532 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.8481. Min Act: -0.1700
Data Index: 8452303 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.8168. Min Act: -0.1700
Data Index: 1867111 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.7856. Min Act: -0.1700
Data Index: 1502223 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.7856. Min Act: -0.1700
Data Index: 6216338 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.7543. Min Act: -0.1700
Data Index: 4576269 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.6918. Min Act: -0.1700
Data Index: 1676931 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.6606. Min Act: -0.1700
Data Index: 857173 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.6606. Min Act: -0.1700
Data Index: 6462969 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.6606. Min Act: -0.1700
Data Index: 903362 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.6293. Min Act: -0.1700
Data Index: 2681293 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.5981. Min Act: -0.1700
Data Index: 4307183 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.5981. Min Act: -0.1700
Data Index: 5214583 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.5981. Min Act: -0.1700
Data Index: 895780 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.5668. Min Act: -0.1700
Data Index: 8601244 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.5668. Min Act: -0.1700
Data Index: 8674825 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.5668. Min Act: -0.1700
Data Index: 1749602 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.5668. Min Act: -0.1700
Data Index: 2716144 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.5981. Min Act: -0.1700
Data Index: 62921 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9106. Min Range: -5.9106
Max Act: 5.5043. Min Act: -0.1700
Data Index: 1016695 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19