Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1395 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3868. Min Range: -5.3868
Max Act: 5.3868. Min Act: -0.1700
Data Index: 6765998 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3868. Min Range: -5.3868
Max Act: 5.3868. Min Act: -0.1700
Data Index: 475199 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3868. Min Range: -5.3868
Max Act: 5.3555. Min Act: -0.1700
Data Index: 3309952 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3868. Min Range: -5.3868
Max Act: 5.1680. Min Act: -0.1700
Data Index: 4090064 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.9493. Min Act: -0.1700
Data Index: 8791879 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.9493. Min Act: -0.1700
Data Index: 6953841 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.9180. Min Act: -0.1700
Data Index: 8545602 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.8868. Min Act: -0.1700
Data Index: 5049238 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.8243. Min Act: -0.1700
Data Index: 309110 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.8243. Min Act: -0.1700
Data Index: 2702384 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.7930. Min Act: -0.1700
Data Index: 8655155 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.8243. Min Act: -0.1700
Data Index: 7127404 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.7618. Min Act: -0.1700
Data Index: 7805591 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.7305. Min Act: -0.1700
Data Index: 5786990 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.7618. Min Act: -0.1700
Data Index: 6924937 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.7618. Min Act: -0.1700
Data Index: 6615673 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.7305. Min Act: -0.1700
Data Index: 694376 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.7618. Min Act: -0.1700
Data Index: 5515238 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.7305. Min Act: -0.1700
Data Index: 1047057 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3868. Min Range: -5.3868
Max Act: 4.7305. Min Act: -0.1700
Data Index: 3148598 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19