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

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

Neuron 5101 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: 3.5370. Min Range: -3.5370

Max Act: 3.5370. Min Act: -0.0000

Data Index: 216382 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 3.5370. Min Range: -3.5370

Max Act: 3.3176. Min Act: -0.0000

Data Index: 1261595 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 3.5370. Min Range: -3.5370

Max Act: 3.2780. Min Act: -0.0000

Data Index: 858220 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 3.5370. Min Range: -3.5370

Max Act: 3.1097. Min Act: -0.0000

Data Index: 1198283 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 3.5370. Min Range: -3.5370

Max Act: 3.0520. Min Act: -0.0000

Data Index: 808257 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.7334. Min Act: -0.0000

Data Index: 539678 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.6902. Min Act: -0.0000

Data Index: 296422 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.7698. Min Act: -0.0000

Data Index: 84520 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.6707. Min Act: -0.0000

Data Index: 103558 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.3926. Min Act: -0.0000

Data Index: 957690 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.5631. Min Act: -0.0000

Data Index: 418097 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.3518. Min Act: -0.0000

Data Index: 962501 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.4244. Min Act: -0.0000

Data Index: 88401 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.3599. Min Act: -0.0000

Data Index: 675603 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.2839. Min Act: -0.0000

Data Index: 810408 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.2848. Min Act: -0.0000

Data Index: 1079622 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.3737. Min Act: -0.0000

Data Index: 745584 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.2743. Min Act: -0.0000

Data Index: 374 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.2275. Min Act: -0.0000

Data Index: 641193 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.2225. Min Act: -0.0000

Data Index: 1287048 (C4 (Web Text))

Max Activating Token Index: 901