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

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

Neuron 4136 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2448. Min Act: -0.0003

Data Index: 900730 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2365. Min Act: -0.0003

Data Index: 712233 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2390. Min Act: -0.0003

Data Index: 1253505 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2364. Min Act: -0.0003

Data Index: 1267693 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2327. Min Act: -0.0003

Data Index: 1214229 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2273. Min Act: -0.0003

Data Index: 1237764 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2115. Min Act: -0.0003

Data Index: 374316 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2105. Min Act: -0.0003

Data Index: 314563 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2172. Min Act: -0.0003

Data Index: 273370 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2131. Min Act: -0.0003

Data Index: 376150 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2137. Min Act: -0.0003

Data Index: 1272889 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2127. Min Act: -0.0003

Data Index: 166232 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2042. Min Act: -0.0003

Data Index: 170457 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2082. Min Act: -0.0003

Data Index: 1081331 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2069. Min Act: -0.0003

Data Index: 122896 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2067. Min Act: -0.0003

Data Index: 316269 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2000. Min Act: -0.0003

Data Index: 917190 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1991. Min Act: -0.0003

Data Index: 650985 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2054. Min Act: -0.0003

Data Index: 392916 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1929. Min Act: -0.0003

Data Index: 675824 (C4 (Web Text))

Max Activating Token Index: 674