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

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

Neuron 253 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: 0.0293. Min Range: -0.0293

Max Act: 0.0293. Min Act: -0.0006

Data Index: 849192 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0275. Min Act: -0.0006

Data Index: 377308 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1563322 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0253. Min Act: -0.0006

Data Index: 793599 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0244. Min Act: -0.0006

Data Index: 74507 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0231. Min Act: -0.0006

Data Index: 428463 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0215. Min Act: -0.0006

Data Index: 882485 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0226. Min Act: -0.0006

Data Index: 516424 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1105204 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1088156 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1483177 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0207. Min Act: -0.0006

Data Index: 511419 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1648825 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1381627 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0208. Min Act: -0.0005

Data Index: 1430843 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1395208 (Python Code)

Max Activating Token Index: 510

Text #16

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0198. Min Act: -0.0006

Data Index: 744226 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1299648 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1291942 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0203. Min Act: -0.0006

Data Index: 338270 (C4 (Web Text))

Max Activating Token Index: 521