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

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

Neuron 1950 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.6415. Min Act: -0.0000

Data Index: 296548 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1280605 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5872. Min Act: -0.0000

Data Index: 389540 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5739. Min Act: -0.0000

Data Index: 882807 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5828. Min Act: -0.0000

Data Index: 421249 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5488. Min Act: -0.0000

Data Index: 485558 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5270. Min Act: -0.0000

Data Index: 333002 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4767. Min Act: -0.0001

Data Index: 489015 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1036607 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1295071 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4493. Min Act: -0.0000

Data Index: 478623 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4468. Min Act: -0.0000

Data Index: 823138 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4397. Min Act: -0.0000

Data Index: 884578 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1259986 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1241020 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4193. Min Act: -0.0000

Data Index: 36722 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4264. Min Act: -0.0000

Data Index: 96481 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.3983. Min Act: -0.0000

Data Index: 276522 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4224. Min Act: -0.0000

Data Index: 644389 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4131. Min Act: -0.0000

Data Index: 71906 (C4 (Web Text))

Max Activating Token Index: 526