Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3823 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.9197. Min Act: -0.0001

Data Index: 162844 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 1.2536. Min Range: -1.2536

Max Act: 1.0921. Min Act: -0.0001

Data Index: 803746 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.2536. Min Range: -1.2536

Max Act: 1.0487. Min Act: -0.0001

Data Index: 848971 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 1.2536. Min Range: -1.2536

Max Act: 1.2536. Min Act: -0.0001

Data Index: 1094723 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 1.2536. Min Range: -1.2536

Max Act: 1.1042. Min Act: -0.0001

Data Index: 207942 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 1.2536. Min Range: -1.2536

Max Act: 1.0136. Min Act: -0.0001

Data Index: 603588 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.9813. Min Act: -0.0001

Data Index: 147070 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.9618. Min Act: -0.0001

Data Index: 497991 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 1.2536. Min Range: -1.2536

Max Act: 1.0121. Min Act: -0.0001

Data Index: 530435 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.8971. Min Act: -0.0001

Data Index: 389004 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.9214. Min Act: -0.0001

Data Index: 126425 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.9636. Min Act: -0.0001

Data Index: 237372 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.9281. Min Act: -0.0001

Data Index: 8300 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.8921. Min Act: -0.0001

Data Index: 459274 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.7401. Min Act: -0.0001

Data Index: 1223742 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.9208. Min Act: -0.0001

Data Index: 121053 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.8246. Min Act: -0.0001

Data Index: 278393 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.8156. Min Act: -0.0001

Data Index: 281412 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.9138. Min Act: -0.0001

Data Index: 93040 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 1.2536. Min Range: -1.2536

Max Act: 0.8168. Min Act: -0.0001

Data Index: 79084 (C4 (Web Text))

Max Activating Token Index: 152