Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5886 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.2393. Min Act: -0.0001

Data Index: 1029880 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3544. Min Act: -0.0001

Data Index: 160958 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.1246. Min Act: -0.0001

Data Index: 1335906 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.0682. Min Act: -0.0001

Data Index: 876102 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9345. Min Act: -0.0001

Data Index: 1288440 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9717. Min Act: -0.0001

Data Index: 1329639 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.0021. Min Act: -0.0001

Data Index: 359004 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9735. Min Act: -0.0001

Data Index: 1199145 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.8293. Min Act: -0.0001

Data Index: 436783 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.8928. Min Act: -0.0001

Data Index: 568280 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9682. Min Act: -0.0001

Data Index: 1281585 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.7986. Min Act: -0.0001

Data Index: 922240 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9296. Min Act: -0.0001

Data Index: 772563 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.8393. Min Act: -0.0001

Data Index: 853915 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.8770. Min Act: -0.0001

Data Index: 24452 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9327. Min Act: -0.0001

Data Index: 1357969 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.8397. Min Act: -0.0001

Data Index: 197796 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.8613. Min Act: -0.0001

Data Index: 682653 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.8272. Min Act: -0.0001

Data Index: 118704 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.8600. Min Act: -0.0001

Data Index: 1318871 (C4 (Web Text))

Max Activating Token Index: 284