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

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

Neuron 4826 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0636. Min Act: -0.0002

Data Index: 316917 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0506. Min Act: -0.0002

Data Index: 92360 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0518. Min Act: -0.0002

Data Index: 430522 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0475. Min Act: -0.0002

Data Index: 115512 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0488. Min Act: -0.0002

Data Index: 149172 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1161751 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1155118 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0473. Min Act: -0.0002

Data Index: 851956 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1415916 (Python Code)

Max Activating Token Index: 110

Text #9

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1506685 (Python Code)

Max Activating Token Index: 899

Text #10

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1205671 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0447. Min Act: -0.0002

Data Index: 579356 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0486. Min Act: -0.0002

Data Index: 917777 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0426. Min Act: -0.0002

Data Index: 38759 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1015093 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1422260 (Python Code)

Max Activating Token Index: 937

Text #16

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0395. Min Act: -0.0002

Data Index: 7935 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1201349 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1519847 (Python Code)

Max Activating Token Index: 946

Text #19

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0448. Min Act: -0.0002

Data Index: 289041 (C4 (Web Text))

Max Activating Token Index: 172