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

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

Neuron 1580 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: 4.1422. Min Range: -4.1422

Max Act: 4.1422. Min Act: -0.0000

Data Index: 287978 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 4.1422. Min Range: -4.1422

Max Act: 3.7515. Min Act: -0.0000

Data Index: 1425634 (Python Code)

Max Activating Token Index: 642

Text #2

Max Range: 4.1422. Min Range: -4.1422

Max Act: 3.4053. Min Act: -0.0000

Data Index: 945097 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 4.1422. Min Range: -4.1422

Max Act: 3.2247. Min Act: -0.0000

Data Index: 618244 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 4.1422. Min Range: -4.1422

Max Act: 3.3663. Min Act: -0.0000

Data Index: 1074527 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 4.1422. Min Range: -4.1422

Max Act: 3.3167. Min Act: -0.0000

Data Index: 1221736 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 4.1422. Min Range: -4.1422

Max Act: 3.0094. Min Act: -0.0000

Data Index: 851684 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 4.1422. Min Range: -4.1422

Max Act: 3.1293. Min Act: -0.0000

Data Index: 714625 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 4.1422. Min Range: -4.1422

Max Act: 3.1099. Min Act: -0.0000

Data Index: 1123820 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 4.1422. Min Range: -4.1422

Max Act: 3.0393. Min Act: -0.0000

Data Index: 662093 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 4.1422. Min Range: -4.1422

Max Act: 2.8986. Min Act: -0.0000

Data Index: 900012 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 4.1422. Min Range: -4.1422

Max Act: 3.0011. Min Act: -0.0000

Data Index: 790082 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 4.1422. Min Range: -4.1422

Max Act: 2.9860. Min Act: -0.0000

Data Index: 215774 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 4.1422. Min Range: -4.1422

Max Act: 2.9647. Min Act: -0.0000

Data Index: 900818 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 4.1422. Min Range: -4.1422

Max Act: 2.9245. Min Act: -0.0000

Data Index: 742905 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 4.1422. Min Range: -4.1422

Max Act: 2.9278. Min Act: -0.0000

Data Index: 1185361 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 4.1422. Min Range: -4.1422

Max Act: 2.8860. Min Act: -0.0000

Data Index: 489223 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 4.1422. Min Range: -4.1422

Max Act: 2.7227. Min Act: -0.0000

Data Index: 1168417 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 4.1422. Min Range: -4.1422

Max Act: 2.8301. Min Act: -0.0000

Data Index: 82276 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 4.1422. Min Range: -4.1422

Max Act: 2.8115. Min Act: -0.0000

Data Index: 903626 (C4 (Web Text))

Max Activating Token Index: 628