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

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

Neuron 1973 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1610. Min Act: -0.0005

Data Index: 118595 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1619. Min Act: -0.0005

Data Index: 388680 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1439. Min Act: -0.0005

Data Index: 825658 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1361. Min Act: -0.0005

Data Index: 1148809 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1356. Min Act: -0.0005

Data Index: 1105224 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1382. Min Act: -0.0005

Data Index: 377143 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1337. Min Act: -0.0005

Data Index: 943334 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1238. Min Act: -0.0005

Data Index: 1266146 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1321. Min Act: -0.0005

Data Index: 1185448 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1210. Min Act: -0.0005

Data Index: 762783 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1194. Min Act: -0.0005

Data Index: 463324 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1234. Min Act: -0.0005

Data Index: 730440 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1163. Min Act: -0.0005

Data Index: 1117410 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1198. Min Act: -0.0005

Data Index: 760811 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1234. Min Act: -0.0005

Data Index: 384361 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1196. Min Act: -0.0005

Data Index: 180137 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1231. Min Act: -0.0005

Data Index: 1047860 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1136. Min Act: -0.0005

Data Index: 99977 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1128. Min Act: -0.0005

Data Index: 841658 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1131. Min Act: -0.0005

Data Index: 573889 (C4 (Web Text))

Max Activating Token Index: 629