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

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

Neuron 3042 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1207364 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.3039. Min Act: -0.0000

Data Index: 670534 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2769. Min Act: -0.0000

Data Index: 665614 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2658. Min Act: -0.0000

Data Index: 148717 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1256297 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2617. Min Act: -0.0000

Data Index: 523483 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1051268 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2538. Min Act: -0.0000

Data Index: 837356 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2592. Min Act: -0.0000

Data Index: 192488 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2500. Min Act: -0.0000

Data Index: 96898 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2339. Min Act: -0.0000

Data Index: 724116 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2352. Min Act: -0.0000

Data Index: 711429 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2435. Min Act: -0.0000

Data Index: 526261 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2348. Min Act: -0.0000

Data Index: 1236879 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1162768 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2285. Min Act: -0.0000

Data Index: 746460 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1086349 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2182. Min Act: -0.0000

Data Index: 899999 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2252. Min Act: -0.0000

Data Index: 372337 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1203210 (C4 (Web Text))

Max Activating Token Index: 231