Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 533 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1632. Min Act: -0.0005

Data Index: 1117842 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1605. Min Act: -0.0005

Data Index: 215817 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1474. Min Act: -0.0005

Data Index: 397559 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1470. Min Act: -0.0005

Data Index: 455199 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1384. Min Act: -0.0005

Data Index: 510731 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1358. Min Act: -0.0005

Data Index: 1155258 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1298. Min Act: -0.0005

Data Index: 687482 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1294. Min Act: -0.0005

Data Index: 876531 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1291. Min Act: -0.0005

Data Index: 587105 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1241. Min Act: -0.0005

Data Index: 107651 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1278. Min Act: -0.0005

Data Index: 878529 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1216. Min Act: -0.0005

Data Index: 1184320 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1206. Min Act: -0.0005

Data Index: 114651 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1250. Min Act: -0.0005

Data Index: 1110572 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1210. Min Act: -0.0005

Data Index: 208734 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1236. Min Act: -0.0005

Data Index: 841434 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1191. Min Act: -0.0005

Data Index: 731558 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1232. Min Act: -0.0005

Data Index: 767738 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1271. Min Act: -0.0005

Data Index: 200675 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1220. Min Act: -0.0005

Data Index: 80786 (C4 (Web Text))

Max Activating Token Index: 548