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

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

Neuron 1412 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3224. Min Act: -0.0001

Data Index: 639749 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2704. Min Act: -0.0001

Data Index: 337737 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2536. Min Act: -0.0001

Data Index: 713142 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2636. Min Act: -0.0001

Data Index: 30176 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2362. Min Act: -0.0001

Data Index: 1045463 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2387. Min Act: -0.0001

Data Index: 487562 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2207. Min Act: -0.0002

Data Index: 952412 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2352. Min Act: -0.0002

Data Index: 1245414 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2265. Min Act: -0.0002

Data Index: 485924 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2242. Min Act: -0.0002

Data Index: 804444 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2180. Min Act: -0.0002

Data Index: 1188037 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2167. Min Act: -0.0002

Data Index: 55635 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2064. Min Act: -0.0001

Data Index: 824406 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2202. Min Act: -0.0001

Data Index: 1055582 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2148. Min Act: -0.0001

Data Index: 618972 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2422. Min Act: -0.0001

Data Index: 357563 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2137. Min Act: -0.0001

Data Index: 264787 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2364. Min Act: -0.0001

Data Index: 824701 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2276. Min Act: -0.0002

Data Index: 19317 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2435. Min Act: -0.0002

Data Index: 210385 (C4 (Web Text))

Max Activating Token Index: 347