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

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

Neuron 17 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.9597. Min Act: -0.0000

Data Index: 96971 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.9419. Min Act: -0.0000

Data Index: 266235 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1169767 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.9223. Min Act: -0.0000

Data Index: 198463 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1027123 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8817. Min Act: -0.0000

Data Index: 77980 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8441. Min Act: -0.0000

Data Index: 251693 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8250. Min Act: -0.0000

Data Index: 767368 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8464. Min Act: -0.0000

Data Index: 802449 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1312657 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7510. Min Act: -0.0000

Data Index: 498494 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.6847. Min Act: -0.0000

Data Index: 250363 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7192. Min Act: -0.0000

Data Index: 338255 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7164. Min Act: -0.0000

Data Index: 727817 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1082664 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7044. Min Act: -0.0000

Data Index: 562960 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.6874. Min Act: -0.0000

Data Index: 62223 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7384. Min Act: -0.0000

Data Index: 591572 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.6682. Min Act: -0.0000

Data Index: 220940 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7363. Min Act: -0.0000

Data Index: 909823 (C4 (Web Text))

Max Activating Token Index: 283