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

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

Neuron 578 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: 0.7366. Min Range: -0.7366

Max Act: 0.7366. Min Act: -0.0000

Data Index: 279179 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1293618 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.7091. Min Act: -0.0000

Data Index: 743735 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1192571 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.6113. Min Act: -0.0000

Data Index: 402158 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5908. Min Act: -0.0000

Data Index: 922888 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5935. Min Act: -0.0000

Data Index: 482495 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1207237 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5707. Min Act: -0.0000

Data Index: 536287 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5624. Min Act: -0.0000

Data Index: 149400 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5526. Min Act: -0.0000

Data Index: 280715 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5450. Min Act: -0.0000

Data Index: 574222 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5287. Min Act: -0.0000

Data Index: 16781 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5395. Min Act: -0.0000

Data Index: 707204 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5326. Min Act: -0.0000

Data Index: 817791 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5300. Min Act: -0.0000

Data Index: 279277 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1300902 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5563. Min Act: -0.0000

Data Index: 840443 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1350111 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.7366. Min Range: -0.7366

Max Act: 0.5301. Min Act: -0.0000

Data Index: 45510 (C4 (Web Text))

Max Activating Token Index: 433