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

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

Neuron 3703 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0533. Min Act: -0.0002

Data Index: 24825 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1124283 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0372. Min Act: -0.0002

Data Index: 854162 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0339. Min Act: -0.0002

Data Index: 106306 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1400381 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0349. Min Act: -0.0002

Data Index: 102814 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0338. Min Act: -0.0002

Data Index: 245446 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0321. Min Act: -0.0002

Data Index: 934391 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0324. Min Act: -0.0002

Data Index: 501672 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1192264 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1083510 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1137988 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0321. Min Act: -0.0002

Data Index: 259474 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0327. Min Act: -0.0002

Data Index: 527743 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0330. Min Act: -0.0002

Data Index: 934997 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0301. Min Act: -0.0002

Data Index: 972440 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0306. Min Act: -0.0002

Data Index: 292151 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1415690 (Python Code)

Max Activating Token Index: 268

Text #18

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0301. Min Act: -0.0002

Data Index: 244956 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0299. Min Act: -0.0002

Data Index: 490711 (C4 (Web Text))

Max Activating Token Index: 4