Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4954 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.4135. Min Range: -6.4135

Max Act: 6.4135. Min Act: -0.0000

Data Index: 140596 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 6.4135. Min Range: -6.4135

Max Act: 6.3363. Min Act: -0.0000

Data Index: 757595 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 6.4135. Min Range: -6.4135

Max Act: 6.0561. Min Act: -0.0000

Data Index: 468162 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 6.4135. Min Range: -6.4135

Max Act: 6.1480. Min Act: -0.0000

Data Index: 239329 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 6.4135. Min Range: -6.4135

Max Act: 6.1391. Min Act: -0.0000

Data Index: 165748 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 6.4135. Min Range: -6.4135

Max Act: 6.2935. Min Act: -0.0000

Data Index: 806621 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 6.4135. Min Range: -6.4135

Max Act: 5.8798. Min Act: -0.0000

Data Index: 1226577 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 6.4135. Min Range: -6.4135

Max Act: 6.0622. Min Act: -0.0000

Data Index: 702650 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 6.4135. Min Range: -6.4135

Max Act: 5.8598. Min Act: -0.0000

Data Index: 278469 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 6.4135. Min Range: -6.4135

Max Act: 5.6261. Min Act: -0.0000

Data Index: 1315880 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 6.4135. Min Range: -6.4135

Max Act: 5.9404. Min Act: -0.0000

Data Index: 918117 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 6.4135. Min Range: -6.4135

Max Act: 5.4334. Min Act: -0.0000

Data Index: 1175832 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 6.4135. Min Range: -6.4135

Max Act: 5.6185. Min Act: -0.0000

Data Index: 319114 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 6.4135. Min Range: -6.4135

Max Act: 5.5286. Min Act: -0.0000

Data Index: 343539 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 6.4135. Min Range: -6.4135

Max Act: 5.4728. Min Act: -0.0000

Data Index: 580468 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 6.4135. Min Range: -6.4135

Max Act: 5.6827. Min Act: -0.0000

Data Index: 1266635 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 6.4135. Min Range: -6.4135

Max Act: 5.1018. Min Act: -0.0000

Data Index: 413105 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 6.4135. Min Range: -6.4135

Max Act: 5.2863. Min Act: -0.0000

Data Index: 998384 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 6.4135. Min Range: -6.4135

Max Act: 5.1872. Min Act: -0.0000

Data Index: 374676 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 6.4135. Min Range: -6.4135

Max Act: 5.1686. Min Act: -0.0000

Data Index: 229162 (C4 (Web Text))

Max Activating Token Index: 569