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

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

Neuron 2824 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1045572 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.4289. Min Act: -0.0000

Data Index: 794134 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3577. Min Act: -0.0000

Data Index: 39971 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3863. Min Act: -0.0000

Data Index: 757546 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1042351 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1181920 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3505. Min Act: -0.0000

Data Index: 398112 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3377. Min Act: -0.0000

Data Index: 735383 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3334. Min Act: -0.0000

Data Index: 996341 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3336. Min Act: -0.0000

Data Index: 448019 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3184. Min Act: -0.0000

Data Index: 721260 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3514. Min Act: -0.0000

Data Index: 559330 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3592. Min Act: -0.0000

Data Index: 719496 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1195333 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3495. Min Act: -0.0000

Data Index: 1325409 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3384. Min Act: -0.0000

Data Index: 1132914 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3229. Min Act: -0.0000

Data Index: 790057 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3580. Min Act: -0.0000

Data Index: 722423 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3317. Min Act: -0.0000

Data Index: 640312 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3286. Min Act: -0.0000

Data Index: 265857 (C4 (Web Text))

Max Activating Token Index: 515