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

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

Neuron 366 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.7389. Min Act: -0.0000

Data Index: 316438 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.5017. Min Act: -0.0000

Data Index: 729428 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1333728 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.3371. Min Act: -0.0000

Data Index: 793016 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.3092. Min Act: -0.0000

Data Index: 855346 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.2298. Min Act: -0.0000

Data Index: 947930 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.2032. Min Act: -0.0000

Data Index: 759262 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.0221. Min Act: -0.0000

Data Index: 860141 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.1429. Min Act: -0.0000

Data Index: 666150 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.1465. Min Act: -0.0000

Data Index: 1139199 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.1390. Min Act: -0.0000

Data Index: 230738 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.1176. Min Act: -0.0000

Data Index: 947514 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.1859. Min Act: -0.0000

Data Index: 854235 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.1583. Min Act: -0.0000

Data Index: 592489 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1179246 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.1101. Min Act: -0.0000

Data Index: 907014 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.1414. Min Act: -0.0000

Data Index: 238419 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1289547 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.0903. Min Act: -0.0000

Data Index: 759339 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.0469. Min Act: -0.0000

Data Index: 1067121 (C4 (Web Text))

Max Activating Token Index: 346