Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1734 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1964. Min Act: -0.0001
Data Index: 32448 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.2026. Min Act: -0.0001
Data Index: 604513 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1824. Min Act: -0.0001
Data Index: 283692 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1840. Min Act: -0.0001
Data Index: 1096554 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1712. Min Act: -0.0001
Data Index: 810119 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1724. Min Act: -0.0001
Data Index: 840341 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1682. Min Act: -0.0001
Data Index: 518382 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1702. Min Act: -0.0001
Data Index: 544625 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1581. Min Act: -0.0001
Data Index: 617868 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1517. Min Act: -0.0001
Data Index: 347328 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1617. Min Act: -0.0001
Data Index: 196677 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1584. Min Act: -0.0001
Data Index: 13133 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1597. Min Act: -0.0001
Data Index: 242075 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1478. Min Act: -0.0001
Data Index: 290132 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1496. Min Act: -0.0001
Data Index: 922870 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1378. Min Act: -0.0001
Data Index: 532170 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1569. Min Act: -0.0001
Data Index: 870657 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1727. Min Act: -0.0001
Data Index: 135488 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1468. Min Act: -0.0001
Data Index: 827772 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2026. Min Range: -0.2026
Max Act: 0.1408. Min Act: -0.0001
Data Index: 274547 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19