Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3492. Min Range: -6.3492
Max Act: 6.3492. Min Act: -0.1700
Data Index: 8305332 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3492. Min Range: -6.3492
Max Act: 6.3492. Min Act: -0.1700
Data Index: 1012789 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3492. Min Range: -6.3492
Max Act: 6.2242. Min Act: -0.1700
Data Index: 5347669 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3492. Min Range: -6.3492
Max Act: 6.0680. Min Act: -0.1700
Data Index: 7167309 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3492. Min Range: -6.3492
Max Act: 6.0367. Min Act: -0.1700
Data Index: 5940364 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3492. Min Range: -6.3492
Max Act: 6.0680. Min Act: -0.1700
Data Index: 1961323 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3492. Min Range: -6.3492
Max Act: 6.0680. Min Act: -0.1700
Data Index: 2562347 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3492. Min Range: -6.3492
Max Act: 6.0680. Min Act: -0.1700
Data Index: 8622823 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3492. Min Range: -6.3492
Max Act: 6.0055. Min Act: -0.1700
Data Index: 1370316 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3492. Min Range: -6.3492
Max Act: 5.9742. Min Act: -0.1700
Data Index: 2221761 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3492. Min Range: -6.3492
Max Act: 5.9430. Min Act: -0.1700
Data Index: 8611253 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3492. Min Range: -6.3492
Max Act: 5.9430. Min Act: -0.1700
Data Index: 1258823 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3492. Min Range: -6.3492
Max Act: 5.9742. Min Act: -0.1700
Data Index: 47025 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3492. Min Range: -6.3492
Max Act: 5.9117. Min Act: -0.1700
Data Index: 8155071 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3492. Min Range: -6.3492
Max Act: 5.9117. Min Act: -0.1700
Data Index: 2408896 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3492. Min Range: -6.3492
Max Act: 5.9117. Min Act: -0.1700
Data Index: 7176107 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3492. Min Range: -6.3492
Max Act: 5.8805. Min Act: -0.1700
Data Index: 2967030 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3492. Min Range: -6.3492
Max Act: 5.8805. Min Act: -0.1700
Data Index: 8372721 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3492. Min Range: -6.3492
Max Act: 5.8805. Min Act: -0.1700
Data Index: 5909377 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3492. Min Range: -6.3492
Max Act: 5.8805. Min Act: -0.1700
Data Index: 7564236 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19