Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.5584. Min Act: -0.1700
Data Index: 2990229 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.2919. Min Act: -0.1700
Data Index: 5509487 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.2762. Min Act: -0.1700
Data Index: 2442545 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.2290. Min Act: -0.1700
Data Index: 699988 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.2448. Min Act: -0.1700
Data Index: 7628512 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.2290. Min Act: -0.1700
Data Index: 4123655 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.2133. Min Act: -0.1700
Data Index: 664315 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.2133. Min Act: -0.1700
Data Index: 5155063 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.1976. Min Act: -0.1700
Data Index: 1212738 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.1819. Min Act: -0.1700
Data Index: 32054 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.1976. Min Act: -0.1700
Data Index: 6859240 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.1661. Min Act: -0.1700
Data Index: 525677 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.1661. Min Act: -0.1700
Data Index: 1727393 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.1661. Min Act: -0.1700
Data Index: 8111898 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.1661. Min Act: -0.1700
Data Index: 3519167 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.1661. Min Act: -0.1700
Data Index: 6555621 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.1347. Min Act: -0.1700
Data Index: 2741648 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.1189. Min Act: -0.1700
Data Index: 4333393 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.1504. Min Act: -0.1700
Data Index: 107522 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5584. Min Range: -3.5584
Max Act: 3.1504. Min Act: -0.1700
Data Index: 5637898 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19