Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3460 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.4922. Min Act: -0.0000

Data Index: 199456 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.4358. Min Act: -0.0000

Data Index: 511006 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3701. Min Act: -0.0000

Data Index: 677710 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3066. Min Act: -0.0000

Data Index: 306237 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2936. Min Act: -0.0000

Data Index: 822352 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2583. Min Act: -0.0000

Data Index: 495795 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2484. Min Act: -0.0000

Data Index: 878655 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1049762 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2616. Min Act: -0.0000

Data Index: 156820 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2607. Min Act: -0.0000

Data Index: 368666 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2386. Min Act: -0.0000

Data Index: 278334 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2350. Min Act: -0.0000

Data Index: 376056 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2428. Min Act: -0.0000

Data Index: 423493 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2336. Min Act: -0.0000

Data Index: 423827 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1284520 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2382. Min Act: -0.0000

Data Index: 377028 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2133. Min Act: -0.0000

Data Index: 480473 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2142. Min Act: -0.0000

Data Index: 348712 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1272161 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2108. Min Act: -0.0000

Data Index: 973832 (C4 (Web Text))

Max Activating Token Index: 902