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

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

Neuron 372 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.6355. Min Act: -0.0001

Data Index: 231023 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5306. Min Act: -0.0001

Data Index: 1484642 (Python Code)

Max Activating Token Index: 606

Text #2

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5443. Min Act: -0.0002

Data Index: 448251 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.4994. Min Act: -0.0001

Data Index: 1552736 (Python Code)

Max Activating Token Index: 675

Text #4

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5169. Min Act: -0.0002

Data Index: 50545 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5463. Min Act: -0.0001

Data Index: 448572 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5538. Min Act: -0.0001

Data Index: 334282 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5542. Min Act: -0.0001

Data Index: 738554 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5337. Min Act: -0.0002

Data Index: 1109313 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5183. Min Act: -0.0001

Data Index: 1361271 (Python Code)

Max Activating Token Index: 958

Text #10

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5170. Min Act: -0.0001

Data Index: 384440 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5308. Min Act: -0.0001

Data Index: 424298 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5285. Min Act: -0.0001

Data Index: 1437339 (Python Code)

Max Activating Token Index: 765

Text #13

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5057. Min Act: -0.0002

Data Index: 1220825 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.4345. Min Act: -0.0001

Data Index: 889706 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5130. Min Act: -0.0002

Data Index: 1340942 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5006. Min Act: -0.0002

Data Index: 151900 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5030. Min Act: -0.0002

Data Index: 376268 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.5079. Min Act: -0.0002

Data Index: 275640 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.6355. Min Range: -0.6355

Max Act: 0.4275. Min Act: -0.0002

Data Index: 697452 (C4 (Web Text))

Max Activating Token Index: 676