Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 65 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.7384. Min Act: -0.0001
Data Index: 56452 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.7404. Min Act: -0.0001
Data Index: 676324 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.6269. Min Act: -0.0001
Data Index: 1650990 (Python Code)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.6950. Min Act: -0.0001
Data Index: 232085 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.7334. Min Act: -0.0001
Data Index: 182871 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.6514. Min Act: -0.0001
Data Index: 570099 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.6310. Min Act: -0.0001
Data Index: 18787 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.6599. Min Act: -0.0001
Data Index: 544281 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.6161. Min Act: -0.0001
Data Index: 800817 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.6272. Min Act: -0.0001
Data Index: 1042150 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.6099. Min Act: -0.0001
Data Index: 279381 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.5752. Min Act: -0.0001
Data Index: 810330 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.5875. Min Act: -0.0001
Data Index: 2559 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.5800. Min Act: -0.0001
Data Index: 329729 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.5752. Min Act: -0.0001
Data Index: 298941 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.5537. Min Act: -0.0001
Data Index: 741201 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.5876. Min Act: -0.0001
Data Index: 532261 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.5482. Min Act: -0.0001
Data Index: 1373136 (Python Code)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.5823. Min Act: -0.0001
Data Index: 426212 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7404. Min Range: -0.7404
Max Act: 0.5811. Min Act: -0.0001
Data Index: 1350233 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19