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

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

Neuron 3279 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.6240. Min Act: -0.0001

Data Index: 652093 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.5135. Min Act: -0.0001

Data Index: 632665 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.5660. Min Act: -0.0001

Data Index: 130566 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.5421. Min Act: -0.0001

Data Index: 46574 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.5027. Min Act: -0.0001

Data Index: 1191631 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.4034. Min Act: -0.0001

Data Index: 632897 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.3928. Min Act: -0.0001

Data Index: 1346443 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.2886. Min Act: -0.0001

Data Index: 537793 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.2828. Min Act: -0.0000

Data Index: 818234 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.2456. Min Act: -0.0001

Data Index: 141935 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.3892. Min Act: -0.0001

Data Index: 127423 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.2767. Min Act: -0.0001

Data Index: 982326 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1214. Min Act: -0.0001

Data Index: 217040 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1152. Min Act: -0.0001

Data Index: 1296376 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1227018 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.0267. Min Act: -0.0001

Data Index: 1163385 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1565. Min Act: -0.0001

Data Index: 931495 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.2132. Min Act: -0.0001

Data Index: 441493 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.0713. Min Act: -0.0001

Data Index: 1123030 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1340. Min Act: -0.0000

Data Index: 175368 (C4 (Web Text))

Max Activating Token Index: 688