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

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

Neuron 2883 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: 0.7995. Min Range: -0.7995

Max Act: 0.7995. Min Act: -0.0001

Data Index: 102205 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.7425. Min Act: -0.0000

Data Index: 231411 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6907. Min Act: -0.0001

Data Index: 1176469 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6865. Min Act: -0.0001

Data Index: 761231 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6653. Min Act: -0.0001

Data Index: 490019 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6773. Min Act: -0.0001

Data Index: 261829 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6647. Min Act: -0.0001

Data Index: 1204300 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6542. Min Act: -0.0001

Data Index: 320179 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6418. Min Act: -0.0001

Data Index: 919470 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6451. Min Act: -0.0001

Data Index: 740185 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6236. Min Act: -0.0001

Data Index: 110812 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6431. Min Act: -0.0001

Data Index: 645986 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6441. Min Act: -0.0001

Data Index: 892671 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6406. Min Act: -0.0001

Data Index: 981655 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6381. Min Act: -0.0001

Data Index: 76269 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6136. Min Act: -0.0001

Data Index: 378658 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6282. Min Act: -0.0001

Data Index: 1149517 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6104. Min Act: -0.0001

Data Index: 445313 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6217. Min Act: -0.0001

Data Index: 1159225 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.5927. Min Act: -0.0001

Data Index: 52869 (C4 (Web Text))

Max Activating Token Index: 757