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

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

Neuron 2640 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: 0.0476. Min Range: -0.0476

Max Act: 0.0463. Min Act: -0.0002

Data Index: 173672 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1316372 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0356. Min Act: -0.0002

Data Index: 58617 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0329. Min Act: -0.0002

Data Index: 698331 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1312061 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0382. Min Act: -0.0002

Data Index: 769191 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0346. Min Act: -0.0002

Data Index: 396030 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0393. Min Act: -0.0002

Data Index: 548581 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0371. Min Act: -0.0002

Data Index: 551642 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1142208 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0352. Min Act: -0.0002

Data Index: 409335 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0314. Min Act: -0.0002

Data Index: 414034 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0384. Min Act: -0.0002

Data Index: 395613 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1008717 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0355. Min Act: -0.0002

Data Index: 97713 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0355. Min Act: -0.0002

Data Index: 980667 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0370. Min Act: -0.0002

Data Index: 665718 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0351. Min Act: -0.0002

Data Index: 284474 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0353. Min Act: -0.0002

Data Index: 521477 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1216257 (C4 (Web Text))

Max Activating Token Index: 811