Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1636 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.6429. Min Act: -0.1700
Data Index: 4883419 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.6116. Min Act: -0.1700
Data Index: 151328 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.6116. Min Act: -0.1700
Data Index: 5018308 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5960. Min Act: -0.1700
Data Index: 6666926 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5960. Min Act: -0.1700
Data Index: 6666925 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5960. Min Act: -0.1700
Data Index: 6647264 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5803. Min Act: -0.1700
Data Index: 1997022 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5960. Min Act: -0.1700
Data Index: 3542472 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5803. Min Act: -0.1700
Data Index: 2077306 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5803. Min Act: -0.1700
Data Index: 71989 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5490. Min Act: -0.1700
Data Index: 7572298 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5177. Min Act: -0.1700
Data Index: 6666923 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5333. Min Act: -0.1700
Data Index: 6399036 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5333. Min Act: -0.1700
Data Index: 6015983 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5177. Min Act: -0.1700
Data Index: 6015981 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5020. Min Act: -0.1700
Data Index: 5022482 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5177. Min Act: -0.1700
Data Index: 5584676 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5177. Min Act: -0.1700
Data Index: 151329 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5020. Min Act: -0.1700
Data Index: 2995146 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5177. Min Act: -0.1700
Data Index: 3764286 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19