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

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

Neuron 815 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.3268. Min Act: -0.0001

Data Index: 935361 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.3284. Min Act: -0.0001

Data Index: 1106161 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1080200 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2429. Min Act: -0.0000

Data Index: 63763 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2580. Min Act: -0.0000

Data Index: 782207 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2394. Min Act: -0.0000

Data Index: 327895 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2464. Min Act: -0.0000

Data Index: 255840 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2300. Min Act: -0.0001

Data Index: 714760 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2468. Min Act: -0.0000

Data Index: 803822 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2208. Min Act: -0.0000

Data Index: 931209 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2298. Min Act: -0.0000

Data Index: 280265 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2287. Min Act: -0.0000

Data Index: 708807 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1225894 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2318. Min Act: -0.0000

Data Index: 814506 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2184. Min Act: -0.0000

Data Index: 598404 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2342. Min Act: -0.0000

Data Index: 90242 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2179. Min Act: -0.0001

Data Index: 1339833 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2198. Min Act: -0.0000

Data Index: 484573 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1014950 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2214. Min Act: -0.0001

Data Index: 420439 (C4 (Web Text))

Max Activating Token Index: 907