Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5404 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.8340. Min Act: -0.1700
Data Index: 2437258 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.4590. Min Act: -0.1700
Data Index: 8778782 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.3965. Min Act: -0.1700
Data Index: 82348 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.3965. Min Act: -0.1700
Data Index: 6071373 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.3340. Min Act: -0.1700
Data Index: 4015216 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.3340. Min Act: -0.1700
Data Index: 54249 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.3340. Min Act: -0.1700
Data Index: 3904001 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.2715. Min Act: -0.1700
Data Index: 4610086 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.2715. Min Act: -0.1700
Data Index: 5397843 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.2715. Min Act: -0.1700
Data Index: 142858 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.2402. Min Act: -0.1700
Data Index: 1706018 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.1777. Min Act: -0.1700
Data Index: 830417 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.1152. Min Act: -0.1700
Data Index: 6340945 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.0215. Min Act: -0.1700
Data Index: 3036984 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.0840. Min Act: -0.1700
Data Index: 6011267 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.0527. Min Act: -0.1700
Data Index: 4174918 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8340. Min Range: -8.8340
Max Act: 8.0215. Min Act: -0.1700
Data Index: 3817581 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8340. Min Range: -8.8340
Max Act: 7.9902. Min Act: -0.1700
Data Index: 977954 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8340. Min Range: -8.8340
Max Act: 7.9902. Min Act: -0.1700
Data Index: 3644180 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8340. Min Range: -8.8340
Max Act: 7.9277. Min Act: -0.1700
Data Index: 3994110 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19