Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5239 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.7360. Min Range: -13.7360
Max Act: 13.7360. Min Act: -0.1700
Data Index: 7552046 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.7360. Min Range: -13.7360
Max Act: 13.1735. Min Act: -0.1700
Data Index: 739593 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.7360. Min Range: -13.7360
Max Act: 13.1110. Min Act: -0.1700
Data Index: 3393729 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.9860. Min Act: -0.1700
Data Index: 6467989 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.9860. Min Act: -0.1700
Data Index: 2039908 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.9235. Min Act: -0.1699
Data Index: 1448238 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.6735. Min Act: -0.1700
Data Index: 3624977 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.7360. Min Act: -0.1700
Data Index: 7216403 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.6735. Min Act: -0.1700
Data Index: 6284819 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.6735. Min Act: -0.1700
Data Index: 5586483 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.6735. Min Act: -0.1700
Data Index: 8195263 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.6735. Min Act: -0.1700
Data Index: 5957876 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.6735. Min Act: -0.1700
Data Index: 6059910 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.6110. Min Act: -0.1700
Data Index: 8450540 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.6110. Min Act: -0.1700
Data Index: 1694269 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.5485. Min Act: -0.1700
Data Index: 3536306 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.4860. Min Act: -0.1700
Data Index: 3530390 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.5485. Min Act: -0.1698
Data Index: 1036666 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.4860. Min Act: -0.1700
Data Index: 2834514 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.7360. Min Range: -13.7360
Max Act: 12.5485. Min Act: -0.1700
Data Index: 5457113 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19