Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 428 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0300. Min Act: -0.0003

Data Index: 596106 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1074469 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0333. Min Act: -0.0003

Data Index: 817239 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1276029 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0325. Min Act: -0.0003

Data Index: 803353 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0334. Min Act: -0.0003

Data Index: 167860 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1207366 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0335. Min Act: -0.0003

Data Index: 447276 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0322. Min Act: -0.0003

Data Index: 303834 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0310. Min Act: -0.0003

Data Index: 378942 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0307. Min Act: -0.0003

Data Index: 489022 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0300. Min Act: -0.0003

Data Index: 754664 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0293. Min Act: -0.0003

Data Index: 92344 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0303. Min Act: -0.0003

Data Index: 162879 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0305. Min Act: -0.0003

Data Index: 840674 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0296. Min Act: -0.0003

Data Index: 754103 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0293. Min Act: -0.0003

Data Index: 979253 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1197056 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0273. Min Act: -0.0003

Data Index: 773378 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0287. Min Act: -0.0003

Data Index: 559450 (C4 (Web Text))

Max Activating Token Index: 232