Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5073 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.3513. Min Act: -0.1700
Data Index: 6942610 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.3513. Min Act: -0.1700
Data Index: 2332659 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.3356. Min Act: -0.1700
Data Index: 3046445 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.2728. Min Act: -0.1700
Data Index: 7657513 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.2571. Min Act: -0.1700
Data Index: 7205088 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.2257. Min Act: -0.1700
Data Index: 7407297 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.2414. Min Act: -0.1700
Data Index: 2176311 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.2257. Min Act: -0.1700
Data Index: 7818342 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.2100. Min Act: -0.1700
Data Index: 1079927 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.2100. Min Act: -0.1700
Data Index: 6707986 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.2100. Min Act: -0.1700
Data Index: 5691694 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.1942. Min Act: -0.1700
Data Index: 5920668 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.1942. Min Act: -0.1700
Data Index: 4438838 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.1785. Min Act: -0.1700
Data Index: 4696630 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.1785. Min Act: -0.1700
Data Index: 1066152 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.1785. Min Act: -0.1700
Data Index: 3409966 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.1628. Min Act: -0.1700
Data Index: 1119519 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.1470. Min Act: -0.1700
Data Index: 2158238 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.1313. Min Act: -0.1700
Data Index: 7344817 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3513. Min Range: -3.3513
Max Act: 3.1470. Min Act: -0.1700
Data Index: 3444021 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19