Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.8391. Min Act: -0.1700
Data Index: 3075861 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.7765. Min Act: -0.1700
Data Index: 2432142 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.7922. Min Act: -0.1700
Data Index: 6863876 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.6514. Min Act: -0.1700
Data Index: 3513315 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.6358. Min Act: -0.1700
Data Index: 2098270 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.6201. Min Act: -0.1700
Data Index: 3764905 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.6514. Min Act: -0.1700
Data Index: 8007327 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.6358. Min Act: -0.1700
Data Index: 559670 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.6045. Min Act: -0.1700
Data Index: 5144182 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.6045. Min Act: -0.1700
Data Index: 2590183 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.5888. Min Act: -0.1700
Data Index: 1984564 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.6201. Min Act: -0.1700
Data Index: 3881067 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.5732. Min Act: -0.1700
Data Index: 6729970 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.5732. Min Act: -0.1700
Data Index: 2706232 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.5888. Min Act: -0.1700
Data Index: 5385718 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.5575. Min Act: -0.1700
Data Index: 3335470 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.5418. Min Act: -0.1700
Data Index: 8472806 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.5418. Min Act: -0.1700
Data Index: 8094115 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.5418. Min Act: -0.1700
Data Index: 4148485 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8391. Min Range: -3.8391
Max Act: 3.5418. Min Act: -0.1700
Data Index: 6244162 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19