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

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

Neuron 1035 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.7321. Min Act: -0.0000

Data Index: 1179674 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.6974. Min Act: -0.0000

Data Index: 440635 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.4203. Min Act: -0.0000

Data Index: 772506 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.4535. Min Act: -0.0000

Data Index: 1484356 (Python Code)

Max Activating Token Index: 626

Text #4

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.4458. Min Act: -0.0000

Data Index: 875732 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.4761. Min Act: -0.0000

Data Index: 693348 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.2028. Min Act: -0.0000

Data Index: 477297 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.2652. Min Act: -0.0000

Data Index: 595479 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.3478. Min Act: -0.0000

Data Index: 738470 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.3133. Min Act: -0.0000

Data Index: 134461 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.2186. Min Act: -0.0000

Data Index: 795465 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1633559 (Python Code)

Max Activating Token Index: 299

Text #12

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.3578. Min Act: -0.0000

Data Index: 1523838 (Python Code)

Max Activating Token Index: 366

Text #13

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.3028. Min Act: -0.0000

Data Index: 376596 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.1712. Min Act: -0.0000

Data Index: 1248001 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.3040. Min Act: -0.0000

Data Index: 1534751 (Python Code)

Max Activating Token Index: 539

Text #16

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.1945. Min Act: -0.0000

Data Index: 1125228 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.1649. Min Act: -0.0000

Data Index: 1652676 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 1.7321. Min Range: -1.7321

Max Act: 1.2194. Min Act: -0.0000

Data Index: 991289 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 1.7321. Min Range: -1.7321

Max Act: 0.9892. Min Act: -0.0000

Data Index: 246167 (C4 (Web Text))

Max Activating Token Index: 233