Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.7358. Min Act: -0.1700
Data Index: 15031 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.6665. Min Act: -0.1700
Data Index: 6093656 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.6578. Min Act: -0.1700
Data Index: 4632640 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.6404. Min Act: -0.1695
Data Index: 6563467 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.6404. Min Act: -0.1700
Data Index: 871184 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.6229. Min Act: -0.1700
Data Index: 3174178 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.6142. Min Act: -0.1700
Data Index: 3118590 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.6142. Min Act: -0.1700
Data Index: 4187238 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.6142. Min Act: -0.1699
Data Index: 8160141 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.5880. Min Act: -0.1700
Data Index: 5395398 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.5880. Min Act: -0.1699
Data Index: 5631391 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.5880. Min Act: -0.1700
Data Index: 833913 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.5880. Min Act: -0.1700
Data Index: 2695762 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.5880. Min Act: -0.1692
Data Index: 4635745 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.5880. Min Act: -0.1700
Data Index: 8515349 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.5880. Min Act: -0.1700
Data Index: 5057046 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.5705. Min Act: -0.1700
Data Index: 5997383 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.5793. Min Act: -0.1696
Data Index: 5705560 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.5793. Min Act: -0.1700
Data Index: 2536734 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7358. Min Range: -1.7358
Max Act: 1.5705. Min Act: -0.1700
Data Index: 1958279 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19