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

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

Neuron 2057 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1359. Min Range: -3.1359

Max Act: 3.1359. Min Act: -0.0001

Data Index: 422149 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 3.1359. Min Range: -3.1359

Max Act: 2.5125. Min Act: -0.0001

Data Index: 954989 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 3.1359. Min Range: -3.1359

Max Act: 2.3092. Min Act: -0.0001

Data Index: 137951 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 3.1359. Min Range: -3.1359

Max Act: 2.2391. Min Act: -0.0001

Data Index: 63972 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 3.1359. Min Range: -3.1359

Max Act: 2.1334. Min Act: -0.0001

Data Index: 1248459 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 3.1359. Min Range: -3.1359

Max Act: 1.8592. Min Act: -0.0001

Data Index: 1218178 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 3.1359. Min Range: -3.1359

Max Act: 2.0354. Min Act: -0.0001

Data Index: 1282849 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 3.1359. Min Range: -3.1359

Max Act: 1.9199. Min Act: -0.0001

Data Index: 208251 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 3.1359. Min Range: -3.1359

Max Act: 2.1409. Min Act: -0.0001

Data Index: 374899 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 3.1359. Min Range: -3.1359

Max Act: 1.9171. Min Act: -0.0001

Data Index: 273082 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 3.1359. Min Range: -3.1359

Max Act: 1.9911. Min Act: -0.0001

Data Index: 1320468 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 3.1359. Min Range: -3.1359

Max Act: 2.1084. Min Act: -0.0001

Data Index: 566586 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 3.1359. Min Range: -3.1359

Max Act: 1.8645. Min Act: -0.0001

Data Index: 147997 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 3.1359. Min Range: -3.1359

Max Act: 1.8427. Min Act: -0.0001

Data Index: 423372 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 3.1359. Min Range: -3.1359

Max Act: 1.6282. Min Act: -0.0001

Data Index: 1070974 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 3.1359. Min Range: -3.1359

Max Act: 1.9539. Min Act: -0.0001

Data Index: 731994 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 3.1359. Min Range: -3.1359

Max Act: 1.9482. Min Act: -0.0001

Data Index: 1221247 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 3.1359. Min Range: -3.1359

Max Act: 1.9417. Min Act: -0.0001

Data Index: 494407 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 3.1359. Min Range: -3.1359

Max Act: 2.0528. Min Act: -0.0001

Data Index: 166133 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 3.1359. Min Range: -3.1359

Max Act: 1.8324. Min Act: -0.0001

Data Index: 1271712 (C4 (Web Text))

Max Activating Token Index: 748