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

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

Neuron 4770 in Layer 1

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: 1.3171. Min Range: -1.3171

Max Act: 1.3171. Min Act: -0.0002

Data Index: 506445 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.2234. Min Act: -0.0003

Data Index: 114151 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.2145. Min Act: -0.0002

Data Index: 484957 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.2120. Min Act: -0.0003

Data Index: 1075553 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.2022. Min Act: -0.0002

Data Index: 456263 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.2018. Min Act: -0.0002

Data Index: 867155 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1994. Min Act: -0.0002

Data Index: 461241 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1816. Min Act: -0.0003

Data Index: 573553 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1650. Min Act: -0.0002

Data Index: 357870 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1621. Min Act: -0.0002

Data Index: 436658 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1606. Min Act: -0.0002

Data Index: 524760 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1552. Min Act: -0.0003

Data Index: 1082236 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1363. Min Act: -0.0002

Data Index: 585394 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1278. Min Act: -0.0002

Data Index: 817185 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1178. Min Act: -0.0002

Data Index: 1144453 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1272. Min Act: -0.0002

Data Index: 183291 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1205. Min Act: -0.0002

Data Index: 991029 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1217. Min Act: -0.0002

Data Index: 560490 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1121. Min Act: -0.0002

Data Index: 1280423 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1096. Min Act: -0.0002

Data Index: 923204 (C4 (Web Text))

Max Activating Token Index: 822