Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 890 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.7172. Min Act: -0.1700
Data Index: 5661562 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.7172. Min Act: -0.1700
Data Index: 2557714 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.6546. Min Act: -0.1700
Data Index: 1354778 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.6702. Min Act: -0.1700
Data Index: 804841 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.5763. Min Act: -0.1700
Data Index: 7654137 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.5607. Min Act: -0.1700
Data Index: 2498131 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.5294. Min Act: -0.1700
Data Index: 2274732 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.4667. Min Act: -0.1700
Data Index: 1617247 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.4354. Min Act: -0.1700
Data Index: 5662706 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.4354. Min Act: -0.1700
Data Index: 706176 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.4197. Min Act: -0.1700
Data Index: 4509434 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.4197. Min Act: -0.1700
Data Index: 2498133 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.3884. Min Act: -0.1700
Data Index: 620335 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.3727. Min Act: -0.1700
Data Index: 1351539 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.3884. Min Act: -0.1700
Data Index: 4960079 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.3727. Min Act: -0.1700
Data Index: 3490906 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.3413. Min Act: -0.1700
Data Index: 2498139 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.3413. Min Act: -0.1700
Data Index: 7954422 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.3256. Min Act: -0.1700
Data Index: 110290 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7172. Min Range: -3.7172
Max Act: 3.3413. Min Act: -0.1700
Data Index: 6359751 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19