Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3590 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.6328. Min Act: -0.0001

Data Index: 348433 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5759. Min Act: -0.0001

Data Index: 1290385 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5789. Min Act: -0.0001

Data Index: 783309 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5621. Min Act: -0.0000

Data Index: 755107 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5742. Min Act: -0.0001

Data Index: 62229 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5751. Min Act: -0.0001

Data Index: 1233129 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5495. Min Act: -0.0001

Data Index: 48030 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5279. Min Act: -0.0001

Data Index: 436319 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5500. Min Act: -0.0001

Data Index: 453549 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5426. Min Act: -0.0000

Data Index: 709043 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5435. Min Act: -0.0000

Data Index: 283369 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1041895 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4996. Min Act: -0.0001

Data Index: 958469 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5351. Min Act: -0.0001

Data Index: 348316 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5330. Min Act: -0.0001

Data Index: 217930 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5142. Min Act: -0.0001

Data Index: 984313 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5207. Min Act: -0.0001

Data Index: 281553 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5017. Min Act: -0.0001

Data Index: 399350 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5242. Min Act: -0.0001

Data Index: 5681 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5206. Min Act: -0.0001

Data Index: 146409 (C4 (Web Text))

Max Activating Token Index: 449