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

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

Neuron 834 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2765. Min Act: -0.0001

Data Index: 273285 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2618. Min Act: -0.0001

Data Index: 928845 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2459. Min Act: -0.0001

Data Index: 1294829 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2502. Min Act: -0.0001

Data Index: 1250054 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2312. Min Act: -0.0001

Data Index: 1191288 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2412. Min Act: -0.0001

Data Index: 829118 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2391. Min Act: -0.0001

Data Index: 831146 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2354. Min Act: -0.0001

Data Index: 1174531 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2420. Min Act: -0.0001

Data Index: 302084 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2346. Min Act: -0.0001

Data Index: 1003321 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2366. Min Act: -0.0001

Data Index: 1241398 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2177. Min Act: -0.0001

Data Index: 1142771 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2431. Min Act: -0.0001

Data Index: 768808 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2270. Min Act: -0.0001

Data Index: 730334 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2120. Min Act: -0.0001

Data Index: 198586 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2265. Min Act: -0.0001

Data Index: 1275656 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2059. Min Act: -0.0001

Data Index: 1148642 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2256. Min Act: -0.0002

Data Index: 516548 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2343. Min Act: -0.0001

Data Index: 433371 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2236. Min Act: -0.0001

Data Index: 1049667 (C4 (Web Text))

Max Activating Token Index: 482