Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4695 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0992. Min Range: -10.0992
Max Act: 10.0992. Min Act: -0.1700
Data Index: 2809745 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.9742. Min Act: -0.1700
Data Index: 7416916 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.7867. Min Act: -0.1700
Data Index: 4809939 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.7242. Min Act: -0.1700
Data Index: 4767749 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.4117. Min Act: -0.1700
Data Index: 2984891 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.4117. Min Act: -0.1700
Data Index: 5712205 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.2867. Min Act: -0.1700
Data Index: 2215903 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.2867. Min Act: -0.1700
Data Index: 8526710 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.2242. Min Act: -0.1700
Data Index: 3275859 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.2242. Min Act: -0.1700
Data Index: 3352374 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.2242. Min Act: -0.1700
Data Index: 3389096 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.1617. Min Act: -0.1700
Data Index: 3125156 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.0992. Min Act: -0.1700
Data Index: 3310495 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.0367. Min Act: -0.1700
Data Index: 6605374 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.0367. Min Act: -0.1700
Data Index: 3294810 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.0367. Min Act: -0.1700
Data Index: 4704459 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.0367. Min Act: -0.1700
Data Index: 6719284 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0992. Min Range: -10.0992
Max Act: 9.0367. Min Act: -0.1700
Data Index: 3740985 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0992. Min Range: -10.0992
Max Act: 8.9117. Min Act: -0.1700
Data Index: 6493913 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0992. Min Range: -10.0992
Max Act: 8.9117. Min Act: -0.1700
Data Index: 3673040 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19