Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3421 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.5340. Min Act: -0.0002

Data Index: 1118761 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.5222. Min Act: -0.0002

Data Index: 491983 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.5053. Min Act: -0.0002

Data Index: 648759 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.5092. Min Act: -0.0001

Data Index: 1078976 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4745. Min Act: -0.0002

Data Index: 1023478 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4966. Min Act: -0.0002

Data Index: 1131135 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4687. Min Act: -0.0002

Data Index: 1044353 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4766. Min Act: -0.0001

Data Index: 755427 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4783. Min Act: -0.0002

Data Index: 640200 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4634. Min Act: -0.0002

Data Index: 571130 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4439. Min Act: -0.0001

Data Index: 1359335 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4445. Min Act: -0.0002

Data Index: 700896 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4582. Min Act: -0.0002

Data Index: 388621 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4575. Min Act: -0.0002

Data Index: 7911 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4714. Min Act: -0.0001

Data Index: 70751 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4705. Min Act: -0.0002

Data Index: 248458 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4849. Min Act: -0.0001

Data Index: 305817 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4795. Min Act: -0.0001

Data Index: 26927 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4694. Min Act: -0.0002

Data Index: 1251933 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4523. Min Act: -0.0002

Data Index: 81436 (C4 (Web Text))

Max Activating Token Index: 248