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

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

Neuron 2589 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: 2.6032. Min Range: -2.6032

Max Act: 2.6032. Min Act: -0.0000

Data Index: 200738 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.8512. Min Act: -0.0000

Data Index: 498631 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.7173. Min Act: -0.0000

Data Index: 185676 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.7539. Min Act: -0.0000

Data Index: 672068 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.8103. Min Act: -0.0000

Data Index: 1076907 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.7085. Min Act: -0.0000

Data Index: 717979 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.6274. Min Act: -0.0000

Data Index: 1208681 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.5494. Min Act: -0.0000

Data Index: 45936 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.5255. Min Act: -0.0000

Data Index: 581067 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.4355. Min Act: -0.0000

Data Index: 793576 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.4717. Min Act: -0.0000

Data Index: 473992 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.4781. Min Act: -0.0000

Data Index: 8423 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.3911. Min Act: -0.0000

Data Index: 541330 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.3784. Min Act: -0.0000

Data Index: 43670 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.2667. Min Act: -0.0000

Data Index: 1208714 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.3340. Min Act: -0.0000

Data Index: 201643 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.3395. Min Act: -0.0000

Data Index: 568548 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.3708. Min Act: -0.0000

Data Index: 9841 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.2592. Min Act: -0.0000

Data Index: 49256 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.2488. Min Act: -0.0000

Data Index: 321563 (C4 (Web Text))

Max Activating Token Index: 533