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

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

Neuron 4492 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2343. Min Range: -1.2343

Max Act: 1.2343. Min Act: -0.0001

Data Index: 1011731 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.9669. Min Act: -0.0001

Data Index: 810457 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.9382. Min Act: -0.0001

Data Index: 564660 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8844. Min Act: -0.0001

Data Index: 459555 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8712. Min Act: -0.0001

Data Index: 170310 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8623. Min Act: -0.0001

Data Index: 1141113 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8602. Min Act: -0.0001

Data Index: 1258358 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8299. Min Act: -0.0001

Data Index: 982860 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8220. Min Act: -0.0001

Data Index: 299253 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.7783. Min Act: -0.0001

Data Index: 1222014 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8314. Min Act: -0.0001

Data Index: 202996 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8510. Min Act: -0.0001

Data Index: 1210135 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.6834. Min Act: -0.0001

Data Index: 53468 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.7001. Min Act: -0.0001

Data Index: 817913 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.7969. Min Act: -0.0001

Data Index: 928876 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.7602. Min Act: -0.0001

Data Index: 280955 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.7553. Min Act: -0.0001

Data Index: 198965 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.6869. Min Act: -0.0001

Data Index: 1653273 (Python Code)

Max Activating Token Index: 929

Text #18

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.7142. Min Act: -0.0001

Data Index: 1554380 (Python Code)

Max Activating Token Index: 413

Text #19

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.7519. Min Act: -0.0001

Data Index: 1511885 (Python Code)

Max Activating Token Index: 533