Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2348 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.5821. Min Act: -0.1700
Data Index: 7135574 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.5351. Min Act: -0.1700
Data Index: 3189840 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.5351. Min Act: -0.1700
Data Index: 4541886 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.5038. Min Act: -0.1700
Data Index: 1640267 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4725. Min Act: -0.1700
Data Index: 7397003 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4568. Min Act: -0.1700
Data Index: 1262988 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4725. Min Act: -0.1700
Data Index: 1125383 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4412. Min Act: -0.1700
Data Index: 1112875 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4255. Min Act: -0.1700
Data Index: 4302023 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4255. Min Act: -0.1700
Data Index: 2152301 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4098. Min Act: -0.1700
Data Index: 4464896 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4255. Min Act: -0.1700
Data Index: 5748014 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4098. Min Act: -0.1700
Data Index: 8049355 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.3941. Min Act: -0.1700
Data Index: 7247601 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4255. Min Act: -0.1700
Data Index: 383760 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4098. Min Act: -0.1700
Data Index: 4336453 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4098. Min Act: -0.1700
Data Index: 6863505 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4098. Min Act: -0.1700
Data Index: 3315389 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.3941. Min Act: -0.1700
Data Index: 373238 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5821. Min Range: -3.5821
Max Act: 3.4098. Min Act: -0.1700
Data Index: 6492601 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19