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

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

Neuron 908 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0280. Min Act: -0.0006

Data Index: 404333 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0281. Min Act: -0.0006

Data Index: 317800 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0005

Data Index: 34469 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0266. Min Act: -0.0006

Data Index: 683225 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0257. Min Act: -0.0006

Data Index: 714698 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0231. Min Act: -0.0006

Data Index: 221246 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0262. Min Act: -0.0006

Data Index: 820915 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0257. Min Act: -0.0006

Data Index: 284688 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0253. Min Act: -0.0006

Data Index: 1064359 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0249. Min Act: -0.0006

Data Index: 588880 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0244. Min Act: -0.0006

Data Index: 883098 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0198. Min Act: -0.0005

Data Index: 32515 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0247. Min Act: -0.0006

Data Index: 1011282 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0247. Min Act: -0.0005

Data Index: 938076 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0230. Min Act: -0.0005

Data Index: 480411 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1228981 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0251. Min Act: -0.0006

Data Index: 71504 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1027650 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1252196 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0230. Min Act: -0.0006

Data Index: 154513 (C4 (Web Text))

Max Activating Token Index: 935