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

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

Neuron 1671 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: 3.5389. Min Range: -3.5389

Max Act: 3.5389. Min Act: -0.0000

Data Index: 1318814 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.2596. Min Act: -0.0000

Data Index: 905950 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.9436. Min Act: -0.0000

Data Index: 368826 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.0848. Min Act: -0.0000

Data Index: 284206 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.0876. Min Act: -0.0000

Data Index: 388767 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.0254. Min Act: -0.0000

Data Index: 1246216 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.0044. Min Act: -0.0000

Data Index: 101891 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.9705. Min Act: -0.0000

Data Index: 268810 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.8324. Min Act: -0.0000

Data Index: 1027349 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.9618. Min Act: -0.0000

Data Index: 296240 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.8208. Min Act: -0.0000

Data Index: 816289 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.9570. Min Act: -0.0000

Data Index: 281987 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.8028. Min Act: -0.0000

Data Index: 625953 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.9394. Min Act: -0.0000

Data Index: 1178017 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.9389. Min Act: -0.0000

Data Index: 897162 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.9383. Min Act: -0.0000

Data Index: 1352696 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.9357. Min Act: -0.0000

Data Index: 704020 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.7978. Min Act: -0.0000

Data Index: 799757 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.9251. Min Act: -0.0000

Data Index: 220640 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 3.5389. Min Range: -3.5389

Max Act: 2.7846. Min Act: -0.0000

Data Index: 92895 (C4 (Web Text))

Max Activating Token Index: 74