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

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

Neuron 5975 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0424. Min Act: -0.0002

Data Index: 269289 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0404. Min Act: -0.0002

Data Index: 426256 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0381. Min Act: -0.0002

Data Index: 809628 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0371. Min Act: -0.0002

Data Index: 978575 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0345. Min Act: -0.0002

Data Index: 67823 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1183689 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0332. Min Act: -0.0002

Data Index: 991067 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0325. Min Act: -0.0002

Data Index: 333743 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0322. Min Act: -0.0002

Data Index: 298317 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0308. Min Act: -0.0002

Data Index: 876954 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0314. Min Act: -0.0002

Data Index: 112602 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0311. Min Act: -0.0002

Data Index: 454642 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0310. Min Act: -0.0002

Data Index: 300512 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0315. Min Act: -0.0002

Data Index: 752534 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0308. Min Act: -0.0002

Data Index: 987239 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1330436 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0307. Min Act: -0.0002

Data Index: 988623 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0306. Min Act: -0.0002

Data Index: 229441 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0298. Min Act: -0.0002

Data Index: 526306 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0304. Min Act: -0.0002

Data Index: 321523 (C4 (Web Text))

Max Activating Token Index: 327