Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3209 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0877. Min Range: -6.0877
Max Act: 6.0877. Min Act: -0.1700
Data Index: 8825723 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.8377. Min Act: -0.1700
Data Index: 5030347 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.6502. Min Act: -0.1700
Data Index: 6304131 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.6502. Min Act: -0.1700
Data Index: 7368383 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.6502. Min Act: -0.1700
Data Index: 6543632 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.6502. Min Act: -0.1700
Data Index: 6459946 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.5877. Min Act: -0.1700
Data Index: 4988612 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.6190. Min Act: -0.1700
Data Index: 5262010 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.5565. Min Act: -0.1700
Data Index: 8235197 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.5252. Min Act: -0.1700
Data Index: 876527 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.5565. Min Act: -0.1700
Data Index: 4010967 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.5252. Min Act: -0.1700
Data Index: 5047014 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.4940. Min Act: -0.1700
Data Index: 5238044 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.4940. Min Act: -0.1700
Data Index: 8769189 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.4940. Min Act: -0.1700
Data Index: 7732997 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.4940. Min Act: -0.1700
Data Index: 3325284 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.4940. Min Act: -0.1700
Data Index: 6176846 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.4627. Min Act: -0.1700
Data Index: 5615175 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.4627. Min Act: -0.1700
Data Index: 5758205 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0877. Min Range: -6.0877
Max Act: 5.4627. Min Act: -0.1700
Data Index: 1319184 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19