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

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

Neuron 54 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.6315. Min Act: -0.0001

Data Index: 1002376 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.4325. Min Act: -0.0001

Data Index: 298745 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.4613. Min Act: -0.0000

Data Index: 455359 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5288. Min Act: -0.0000

Data Index: 1033070 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.3952. Min Act: -0.0001

Data Index: 1075657 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.3304. Min Act: -0.0001

Data Index: 145382 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.3351. Min Act: -0.0000

Data Index: 1058345 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2326. Min Act: -0.0001

Data Index: 1357716 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2307. Min Act: -0.0000

Data Index: 473493 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2016. Min Act: -0.0000

Data Index: 1268411 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2184. Min Act: -0.0000

Data Index: 286209 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.0554. Min Act: -0.0001

Data Index: 607465 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.1291. Min Act: -0.0001

Data Index: 32400 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.1244. Min Act: -0.0000

Data Index: 669268 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.0937. Min Act: -0.0001

Data Index: 977768 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.1916. Min Act: -0.0001

Data Index: 975462 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.1530. Min Act: -0.0000

Data Index: 261209 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.1006. Min Act: -0.0000

Data Index: 1354014 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.0777. Min Act: -0.0000

Data Index: 204786 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.0167. Min Act: -0.0000

Data Index: 482459 (C4 (Web Text))

Max Activating Token Index: 909