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

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

Neuron 3320 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.3476. Min Act: -0.0002

Data Index: 1058360 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2910. Min Act: -0.0002

Data Index: 792051 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2479. Min Act: -0.0002

Data Index: 46169 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2473. Min Act: -0.0002

Data Index: 1129751 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2517. Min Act: -0.0002

Data Index: 652723 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2344. Min Act: -0.0002

Data Index: 453236 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2133. Min Act: -0.0002

Data Index: 1450195 (Python Code)

Max Activating Token Index: 343

Text #7

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2318. Min Act: -0.0002

Data Index: 1101652 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2530. Min Act: -0.0002

Data Index: 670355 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2116. Min Act: -0.0002

Data Index: 1119787 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2427. Min Act: -0.0002

Data Index: 402416 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2382. Min Act: -0.0002

Data Index: 185324 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2384. Min Act: -0.0002

Data Index: 1004882 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2037. Min Act: -0.0002

Data Index: 1208248 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2202. Min Act: -0.0002

Data Index: 1431632 (Python Code)

Max Activating Token Index: 591

Text #15

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2192. Min Act: -0.0002

Data Index: 328954 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2406. Min Act: -0.0002

Data Index: 592031 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2219. Min Act: -0.0002

Data Index: 669436 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2218. Min Act: -0.0002

Data Index: 805383 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.3476. Min Range: -0.3476

Max Act: 0.2267. Min Act: -0.0002

Data Index: 97721 (C4 (Web Text))

Max Activating Token Index: 40