Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3374 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2620. Min Act: -0.0001

Data Index: 524290 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2327. Min Act: -0.0001

Data Index: 1013387 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2263. Min Act: -0.0001

Data Index: 137937 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2258. Min Act: -0.0001

Data Index: 1554308 (Python Code)

Max Activating Token Index: 779

Text #4

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2278. Min Act: -0.0001

Data Index: 866053 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2282. Min Act: -0.0001

Data Index: 844836 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2216. Min Act: -0.0001

Data Index: 835080 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2192. Min Act: -0.0001

Data Index: 1282789 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2258. Min Act: -0.0001

Data Index: 1143897 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2221. Min Act: -0.0001

Data Index: 1521134 (Python Code)

Max Activating Token Index: 139

Text #10

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2237. Min Act: -0.0001

Data Index: 1304332 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2144. Min Act: -0.0001

Data Index: 870703 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2138. Min Act: -0.0001

Data Index: 421582 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2176. Min Act: -0.0001

Data Index: 1611933 (Python Code)

Max Activating Token Index: 451

Text #14

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2199. Min Act: -0.0001

Data Index: 123964 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2173. Min Act: -0.0001

Data Index: 1322152 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2181. Min Act: -0.0001

Data Index: 933906 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2159. Min Act: -0.0001

Data Index: 1287836 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2116. Min Act: -0.0001

Data Index: 1528035 (Python Code)

Max Activating Token Index: 189

Text #19

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2161. Min Act: -0.0001

Data Index: 732880 (C4 (Web Text))

Max Activating Token Index: 307