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

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

Neuron 130 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.5320. Min Act: -0.0000

Data Index: 435218 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.3022. Min Act: -0.0000

Data Index: 526131 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.0984. Min Act: -0.0000

Data Index: 265571 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.9809. Min Act: -0.0000

Data Index: 80187 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.8966. Min Act: -0.0000

Data Index: 1296071 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.7005. Min Act: -0.0000

Data Index: 494992 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.7311. Min Act: -0.0000

Data Index: 183730 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.6463. Min Act: -0.0000

Data Index: 1091739 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.6921. Min Act: -0.0000

Data Index: 894984 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.5926. Min Act: -0.0000

Data Index: 812361 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.5723. Min Act: -0.0000

Data Index: 1319630 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.5985. Min Act: -0.0000

Data Index: 570388 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.5004. Min Act: -0.0000

Data Index: 30398 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.4661. Min Act: -0.0000

Data Index: 697238 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.4077. Min Act: -0.0000

Data Index: 645629 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.2371. Min Act: -0.0000

Data Index: 33197 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.3779. Min Act: -0.0000

Data Index: 681569 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.3860. Min Act: -0.0000

Data Index: 5972 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.3688. Min Act: -0.0000

Data Index: 566478 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 2.5320. Min Range: -2.5320

Max Act: 1.2399. Min Act: -0.0000

Data Index: 521450 (C4 (Web Text))

Max Activating Token Index: 697