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

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

Neuron 1462 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: 9.2983. Min Range: -9.2983

Max Act: 9.1590. Min Act: -0.0000

Data Index: 129138 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 9.2983. Min Range: -9.2983

Max Act: 9.2983. Min Act: -0.0000

Data Index: 1215806 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.9957. Min Act: -0.0000

Data Index: 713460 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.9510. Min Act: -0.0000

Data Index: 1014276 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.7930. Min Act: -0.0000

Data Index: 1001153 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 9.2983. Min Range: -9.2983

Max Act: 9.0879. Min Act: -0.0000

Data Index: 195376 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 9.2983. Min Range: -9.2983

Max Act: 9.1303. Min Act: -0.0000

Data Index: 55339 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 9.2983. Min Range: -9.2983

Max Act: 9.0534. Min Act: -0.0000

Data Index: 1008580 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.6723. Min Act: -0.0000

Data Index: 388117 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.8111. Min Act: -0.0000

Data Index: 677687 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.6308. Min Act: -0.0000

Data Index: 1124631 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.6145. Min Act: -0.0000

Data Index: 360956 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.7890. Min Act: -0.0000

Data Index: 691157 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.7730. Min Act: -0.0000

Data Index: 1035556 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.7477. Min Act: -0.0000

Data Index: 1194800 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.0882. Min Act: -0.0000

Data Index: 288196 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.3468. Min Act: -0.0000

Data Index: 48624 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.1547. Min Act: -0.0000

Data Index: 642477 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.1399. Min Act: -0.0000

Data Index: 210975 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 9.2983. Min Range: -9.2983

Max Act: 8.2650. Min Act: -0.0000

Data Index: 413796 (C4 (Web Text))

Max Activating Token Index: 73