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

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

Neuron 1893 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3099. Min Range: -2.3099

Max Act: 2.3099. Min Act: -0.0000

Data Index: 615067 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.8478. Min Act: 0.0000

Data Index: 645433 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.7768. Min Act: -0.0000

Data Index: 557530 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.6173. Min Act: -0.0000

Data Index: 894129 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.6980. Min Act: -0.0000

Data Index: 812301 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.5788. Min Act: -0.0000

Data Index: 91039 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.6296. Min Act: -0.0000

Data Index: 850584 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.4584. Min Act: -0.0000

Data Index: 354838 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.4964. Min Act: 0.0000

Data Index: 1038950 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.4465. Min Act: -0.0000

Data Index: 99273 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.4150. Min Act: -0.0000

Data Index: 747592 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.4082. Min Act: -0.0000

Data Index: 119376 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.3194. Min Act: 0.0000

Data Index: 815504 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.3938. Min Act: -0.0000

Data Index: 1170812 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.2672. Min Act: -0.0000

Data Index: 200569 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.2203. Min Act: -0.0000

Data Index: 1321371 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.2226. Min Act: -0.0000

Data Index: 856849 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.2987. Min Act: -0.0000

Data Index: 307086 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.1922. Min Act: -0.0000

Data Index: 1094187 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 2.3099. Min Range: -2.3099

Max Act: 1.1725. Min Act: -0.0000

Data Index: 287045 (C4 (Web Text))

Max Activating Token Index: 419