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

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

Neuron 5262 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: 7.0224. Min Range: -7.0224

Max Act: 7.0224. Min Act: -0.0000

Data Index: 432554 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 7.0224. Min Range: -7.0224

Max Act: 6.8481. Min Act: -0.0000

Data Index: 1262235 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 7.0224. Min Range: -7.0224

Max Act: 6.5918. Min Act: -0.0000

Data Index: 1225239 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 7.0224. Min Range: -7.0224

Max Act: 6.5956. Min Act: -0.0000

Data Index: 1306604 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 7.0224. Min Range: -7.0224

Max Act: 6.7899. Min Act: -0.0000

Data Index: 35326 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 7.0224. Min Range: -7.0224

Max Act: 6.4521. Min Act: -0.0000

Data Index: 816816 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 7.0224. Min Range: -7.0224

Max Act: 6.2338. Min Act: -0.0000

Data Index: 1151229 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 7.0224. Min Range: -7.0224

Max Act: 5.3432. Min Act: -0.0000

Data Index: 95509 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 7.0224. Min Range: -7.0224

Max Act: 3.7812. Min Act: -0.0000

Data Index: 736019 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 7.0224. Min Range: -7.0224

Max Act: 4.0342. Min Act: -0.0000

Data Index: 1250646 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 7.0224. Min Range: -7.0224

Max Act: 3.4484. Min Act: -0.0000

Data Index: 901300 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 7.0224. Min Range: -7.0224

Max Act: 3.4103. Min Act: -0.0000

Data Index: 640653 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 7.0224. Min Range: -7.0224

Max Act: 3.4086. Min Act: -0.0000

Data Index: 273200 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 7.0224. Min Range: -7.0224

Max Act: 3.5803. Min Act: -0.0000

Data Index: 964840 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 7.0224. Min Range: -7.0224

Max Act: 3.5949. Min Act: -0.0000

Data Index: 728653 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 7.0224. Min Range: -7.0224

Max Act: 3.3683. Min Act: -0.0000

Data Index: 914360 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 7.0224. Min Range: -7.0224

Max Act: 3.3308. Min Act: -0.0000

Data Index: 1044054 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 7.0224. Min Range: -7.0224

Max Act: 3.4471. Min Act: -0.0000

Data Index: 342584 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 7.0224. Min Range: -7.0224

Max Act: 3.2723. Min Act: -0.0000

Data Index: 824130 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 7.0224. Min Range: -7.0224

Max Act: 3.2316. Min Act: -0.0000

Data Index: 637850 (C4 (Web Text))

Max Activating Token Index: 818