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

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

Neuron 4314 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1306. Min Act: -0.0001

Data Index: 107148 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1206. Min Act: -0.0001

Data Index: 524490 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1268. Min Act: -0.0001

Data Index: 13622 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1041. Min Act: -0.0001

Data Index: 978808 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1191191 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1040. Min Act: -0.0001

Data Index: 842408 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1243. Min Act: -0.0001

Data Index: 641779 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1176. Min Act: -0.0001

Data Index: 826177 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1090. Min Act: -0.0001

Data Index: 442574 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1244. Min Act: -0.0001

Data Index: 635485 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1283. Min Act: -0.0001

Data Index: 453241 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1242. Min Act: -0.0001

Data Index: 849563 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1192. Min Act: -0.0001

Data Index: 1332696 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1115. Min Act: -0.0001

Data Index: 468959 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1095. Min Act: -0.0001

Data Index: 577996 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1202241 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1091. Min Act: -0.0001

Data Index: 843438 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1097. Min Act: -0.0001

Data Index: 936226 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1157888 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1086. Min Act: -0.0001

Data Index: 285478 (C4 (Web Text))

Max Activating Token Index: 289