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

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

Neuron 1525 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7359. Min Range: -2.7359

Max Act: 2.7359. Min Act: -0.0000

Data Index: 601910 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 2.7359. Min Range: -2.7359

Max Act: 2.4880. Min Act: -0.0000

Data Index: 294212 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 2.7359. Min Range: -2.7359

Max Act: 2.4606. Min Act: -0.0000

Data Index: 252970 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 2.7359. Min Range: -2.7359

Max Act: 2.3416. Min Act: -0.0000

Data Index: 1154586 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 2.7359. Min Range: -2.7359

Max Act: 2.3754. Min Act: -0.0001

Data Index: 1062990 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 2.7359. Min Range: -2.7359

Max Act: 2.2142. Min Act: -0.0000

Data Index: 167573 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 2.7359. Min Range: -2.7359

Max Act: 2.5430. Min Act: -0.0000

Data Index: 1340712 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 2.7359. Min Range: -2.7359

Max Act: 2.0148. Min Act: -0.0000

Data Index: 918189 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 2.7359. Min Range: -2.7359

Max Act: 2.2152. Min Act: -0.0000

Data Index: 161959 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 2.7359. Min Range: -2.7359

Max Act: 1.8649. Min Act: -0.0000

Data Index: 1341486 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 2.7359. Min Range: -2.7359

Max Act: 1.9674. Min Act: -0.0000

Data Index: 106234 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 2.7359. Min Range: -2.7359

Max Act: 2.0534. Min Act: -0.0000

Data Index: 943697 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 2.7359. Min Range: -2.7359

Max Act: 2.1502. Min Act: -0.0000

Data Index: 1099775 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 2.7359. Min Range: -2.7359

Max Act: 2.0376. Min Act: -0.0000

Data Index: 987774 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 2.7359. Min Range: -2.7359

Max Act: 1.8966. Min Act: -0.0000

Data Index: 1125765 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 2.7359. Min Range: -2.7359

Max Act: 1.8557. Min Act: -0.0000

Data Index: 1163925 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 2.7359. Min Range: -2.7359

Max Act: 1.8645. Min Act: -0.0000

Data Index: 758497 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 2.7359. Min Range: -2.7359

Max Act: 1.9594. Min Act: -0.0000

Data Index: 565746 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 2.7359. Min Range: -2.7359

Max Act: 1.9459. Min Act: -0.0000

Data Index: 468631 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 2.7359. Min Range: -2.7359

Max Act: 1.8344. Min Act: -0.0000

Data Index: 715672 (C4 (Web Text))

Max Activating Token Index: 731