Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4873 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1285944 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.0929. Min Act: -0.0000

Data Index: 343839 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 1.2213. Min Range: -1.2213

Max Act: 1.0096. Min Act: -0.0000

Data Index: 682167 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9623. Min Act: -0.0000

Data Index: 316743 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9479. Min Act: -0.0000

Data Index: 120845 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1270083 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8356. Min Act: -0.0000

Data Index: 319155 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1245466 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8687. Min Act: -0.0000

Data Index: 421400 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1033014 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1282460 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8502. Min Act: -0.0000

Data Index: 375440 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8255. Min Act: -0.0000

Data Index: 99008 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1355736 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8178. Min Act: -0.0000

Data Index: 552798 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.7988. Min Act: 0.0000

Data Index: 1337501 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.8054. Min Act: -0.0000

Data Index: 842090 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.7649. Min Act: -0.0000

Data Index: 757010 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1017050 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 1.2213. Min Range: -1.2213

Max Act: 0.7439. Min Act: -0.0000

Data Index: 101091 (C4 (Web Text))

Max Activating Token Index: 456