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

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

Neuron 2742 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4352. Min Range: -3.4352

Max Act: 3.4352. Min Act: -0.0000

Data Index: 79035 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 3.4352. Min Range: -3.4352

Max Act: 3.1598. Min Act: -0.0000

Data Index: 979677 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.8637. Min Act: -0.0000

Data Index: 1197594 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.6364. Min Act: -0.0000

Data Index: 878978 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.7422. Min Act: -0.0000

Data Index: 153473 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.5627. Min Act: -0.0000

Data Index: 1024339 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.4757. Min Act: -0.0000

Data Index: 614651 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.5687. Min Act: -0.0000

Data Index: 397241 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.4590. Min Act: -0.0000

Data Index: 250366 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.6181. Min Act: -0.0000

Data Index: 1280674 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.4444. Min Act: -0.0000

Data Index: 578134 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.3150. Min Act: -0.0000

Data Index: 264823 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.4620. Min Act: -0.0000

Data Index: 492187 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.5809. Min Act: -0.0000

Data Index: 936229 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.4364. Min Act: -0.0000

Data Index: 1281452 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.4507. Min Act: -0.0000

Data Index: 1113963 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.4004. Min Act: -0.0000

Data Index: 45206 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.4028. Min Act: -0.0000

Data Index: 880342 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.3971. Min Act: -0.0000

Data Index: 687624 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 3.4352. Min Range: -3.4352

Max Act: 2.3883. Min Act: -0.0000

Data Index: 895504 (C4 (Web Text))

Max Activating Token Index: 560