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

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

Neuron 1067 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0442. Min Act: -0.0002

Data Index: 346327 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1203312 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0388. Min Act: -0.0002

Data Index: 850635 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1379171 (Python Code)

Max Activating Token Index: 74

Text #4

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1308535 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0376. Min Act: -0.0001

Data Index: 313557 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1072240 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1626682 (Python Code)

Max Activating Token Index: 402

Text #8

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0365. Min Act: -0.0002

Data Index: 790049 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0364. Min Act: -0.0002

Data Index: 265785 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1347403 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0355. Min Act: -0.0002

Data Index: 660078 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0352. Min Act: -0.0002

Data Index: 142742 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1426684 (Python Code)

Max Activating Token Index: 42

Text #14

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1649787 (Python Code)

Max Activating Token Index: 53

Text #15

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1201540 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1546177 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0324. Min Act: -0.0002

Data Index: 650080 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0324. Min Act: -0.0002

Data Index: 330430 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0320. Min Act: -0.0002

Data Index: 588971 (C4 (Web Text))

Max Activating Token Index: 278