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

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

Neuron 517 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.4469. Min Act: -0.0000

Data Index: 529244 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.3486. Min Act: -0.0001

Data Index: 836517 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.8913. Min Act: -0.0000

Data Index: 347684 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.0320. Min Act: -0.0001

Data Index: 265139 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.8307. Min Act: -0.0001

Data Index: 828180 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.9527. Min Act: -0.0000

Data Index: 835780 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.9226. Min Act: -0.0001

Data Index: 1243559 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.9102. Min Act: -0.0001

Data Index: 1176917 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.9727. Min Act: -0.0001

Data Index: 1175302 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.9740. Min Act: -0.0001

Data Index: 1298219 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1135884 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.9079. Min Act: -0.0000

Data Index: 880850 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1198185 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.8758. Min Act: -0.0000

Data Index: 344340 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1153329 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.8033. Min Act: -0.0001

Data Index: 626852 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.8160. Min Act: -0.0000

Data Index: 281583 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.8447. Min Act: -0.0000

Data Index: 206494 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.6569. Min Act: -0.0000

Data Index: 457318 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.9378. Min Act: -0.0000

Data Index: 740782 (C4 (Web Text))

Max Activating Token Index: 19