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

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

Neuron 5985 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2257. Min Range: -2.2257

Max Act: 2.2257. Min Act: -0.0000

Data Index: 523070 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 2.2257. Min Range: -2.2257

Max Act: 2.0706. Min Act: -0.0000

Data Index: 1054996 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 2.2257. Min Range: -2.2257

Max Act: 2.0711. Min Act: -0.0000

Data Index: 857315 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 2.2257. Min Range: -2.2257

Max Act: 2.1683. Min Act: -0.0000

Data Index: 810196 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 2.2257. Min Range: -2.2257

Max Act: 2.0381. Min Act: -0.0000

Data Index: 362347 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 2.2257. Min Range: -2.2257

Max Act: 2.0023. Min Act: -0.0000

Data Index: 356882 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.9259. Min Act: -0.0000

Data Index: 1171661 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.8788. Min Act: -0.0000

Data Index: 170054 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.8234. Min Act: -0.0000

Data Index: 343654 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.8193. Min Act: -0.0000

Data Index: 881679 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.7553. Min Act: -0.0000

Data Index: 151230 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.8498. Min Act: -0.0000

Data Index: 1230608 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.8390. Min Act: -0.0000

Data Index: 1119071 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.7505. Min Act: -0.0000

Data Index: 570815 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.6964. Min Act: -0.0000

Data Index: 589140 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.6804. Min Act: -0.0000

Data Index: 604211 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.7711. Min Act: -0.0000

Data Index: 9485 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.7775. Min Act: -0.0000

Data Index: 663358 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.6435. Min Act: -0.0000

Data Index: 816692 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 2.2257. Min Range: -2.2257

Max Act: 1.6255. Min Act: -0.0000

Data Index: 560947 (C4 (Web Text))

Max Activating Token Index: 334