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

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

Neuron 4906 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: 0.4542. Min Range: -0.4542

Max Act: 0.4528. Min Act: -0.0000

Data Index: 737918 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4542. Min Act: -0.0000

Data Index: 275111 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1197701 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4187. Min Act: -0.0000

Data Index: 273963 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3894. Min Act: -0.0000

Data Index: 458458 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3785. Min Act: -0.0000

Data Index: 407499 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1152332 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1122542 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1273500 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1251669 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3550. Min Act: -0.0000

Data Index: 669660 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3475. Min Act: -0.0000

Data Index: 589037 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3463. Min Act: -0.0000

Data Index: 819815 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3453. Min Act: -0.0000

Data Index: 202701 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1238314 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3321. Min Act: -0.0000

Data Index: 170913 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1200478 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1216460 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3489. Min Act: -0.0000

Data Index: 346172 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3203. Min Act: -0.0000

Data Index: 309838 (C4 (Web Text))

Max Activating Token Index: 630