Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1184 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2757. Min Act: -0.0002

Data Index: 699345 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2619. Min Act: -0.0002

Data Index: 1195358 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2553. Min Act: -0.0002

Data Index: 566669 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2656. Min Act: -0.0002

Data Index: 872540 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2493. Min Act: -0.0002

Data Index: 1014062 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2388. Min Act: -0.0002

Data Index: 379162 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2517. Min Act: -0.0002

Data Index: 218357 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2273. Min Act: -0.0002

Data Index: 890875 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2354. Min Act: -0.0002

Data Index: 1269142 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2305. Min Act: -0.0002

Data Index: 997813 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2263. Min Act: -0.0002

Data Index: 567045 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2271. Min Act: -0.0002

Data Index: 909628 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2126. Min Act: -0.0002

Data Index: 137014 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2258. Min Act: -0.0002

Data Index: 1006005 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2228. Min Act: -0.0002

Data Index: 522163 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2365. Min Act: -0.0002

Data Index: 1159532 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2144. Min Act: -0.0002

Data Index: 34412 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2072. Min Act: -0.0002

Data Index: 1021450 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2098. Min Act: -0.0002

Data Index: 192178 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2074. Min Act: -0.0002

Data Index: 837735 (C4 (Web Text))

Max Activating Token Index: 345