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

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

Neuron 2027 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1418. Min Act: -0.0001

Data Index: 775122 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1334. Min Act: -0.0000

Data Index: 471131 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1089157 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1433. Min Act: -0.0001

Data Index: 857439 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1337. Min Act: -0.0000

Data Index: 784965 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1305. Min Act: -0.0000

Data Index: 533171 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1326. Min Act: -0.0001

Data Index: 142148 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1284. Min Act: -0.0000

Data Index: 51649 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1298089 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1254773 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1238. Min Act: -0.0001

Data Index: 419256 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1190. Min Act: -0.0000

Data Index: 354550 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1160. Min Act: -0.0000

Data Index: 658394 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1187. Min Act: -0.0000

Data Index: 95521 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1195. Min Act: -0.0000

Data Index: 39820 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1130. Min Act: -0.0000

Data Index: 520985 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1223. Min Act: -0.0000

Data Index: 361114 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1176. Min Act: -0.0000

Data Index: 821507 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1092. Min Act: -0.0000

Data Index: 762509 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1031140 (C4 (Web Text))

Max Activating Token Index: 803