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

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

Neuron 2981 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: 0.3161. Min Range: -0.3161

Max Act: 0.3161. Min Act: -0.0001

Data Index: 1055327 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1064223 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2475. Min Act: -0.0001

Data Index: 1096878 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1028187 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2609. Min Act: -0.0001

Data Index: 1073732 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2641. Min Act: -0.0000

Data Index: 818906 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2546. Min Act: -0.0001

Data Index: 600954 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2430. Min Act: -0.0000

Data Index: 145361 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2358. Min Act: -0.0001

Data Index: 884912 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2427. Min Act: -0.0000

Data Index: 491443 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2274. Min Act: -0.0000

Data Index: 484128 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2217. Min Act: -0.0001

Data Index: 844118 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2202. Min Act: -0.0000

Data Index: 62605 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2198. Min Act: -0.0001

Data Index: 115717 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2129. Min Act: -0.0001

Data Index: 1170530 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2116. Min Act: -0.0001

Data Index: 964892 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2260. Min Act: -0.0000

Data Index: 895271 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2116. Min Act: -0.0000

Data Index: 461753 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2394. Min Act: -0.0001

Data Index: 378181 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2148. Min Act: -0.0000

Data Index: 768123 (C4 (Web Text))

Max Activating Token Index: 153