Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2077 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.5969. Min Act: -0.0001
Data Index: 1478093 (Python Code)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.5202. Min Act: -0.0001
Data Index: 387646 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.4574. Min Act: -0.0001
Data Index: 1488611 (Python Code)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.2113. Min Act: -0.0001
Data Index: 53513 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.3197. Min Act: -0.0001
Data Index: 1274828 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.2043. Min Act: -0.0001
Data Index: 737363 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.2955. Min Act: -0.0001
Data Index: 1298633 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.1719. Min Act: -0.0001
Data Index: 789440 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.2189. Min Act: -0.0001
Data Index: 609466 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.1955. Min Act: -0.0001
Data Index: 373703 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.1827. Min Act: -0.0001
Data Index: 1045285 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.1752. Min Act: -0.0001
Data Index: 667040 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.0633. Min Act: -0.0001
Data Index: 670885 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.1580. Min Act: -0.0001
Data Index: 924254 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.2712. Min Act: -0.0001
Data Index: 1520629 (Python Code)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.1518. Min Act: -0.0001
Data Index: 444523 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.1414. Min Act: -0.0001
Data Index: 672615 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.1435. Min Act: -0.0001
Data Index: 942487 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.2369. Min Act: -0.0001
Data Index: 538064 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5969. Min Range: -2.5969
Max Act: 2.0780. Min Act: -0.0001
Data Index: 1074632 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19