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

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

Neuron 2868 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.6339. Min Act: -0.0001

Data Index: 574071 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.6092. Min Act: -0.0001

Data Index: 441677 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.5710. Min Act: -0.0001

Data Index: 6313 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.5491. Min Act: -0.0000

Data Index: 191684 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.5489. Min Act: -0.0001

Data Index: 406282 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.5210. Min Act: -0.0000

Data Index: 95447 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.5403. Min Act: -0.0000

Data Index: 414578 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.5370. Min Act: -0.0001

Data Index: 964116 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4934. Min Act: -0.0001

Data Index: 454391 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.5153. Min Act: -0.0000

Data Index: 23612 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4900. Min Act: -0.0001

Data Index: 652026 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4979. Min Act: -0.0000

Data Index: 427381 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4796. Min Act: -0.0000

Data Index: 253655 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1354977 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4968. Min Act: -0.0001

Data Index: 755303 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1213591 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4784. Min Act: -0.0001

Data Index: 840958 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4878. Min Act: -0.0001

Data Index: 1234867 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4707. Min Act: -0.0001

Data Index: 1468795 (Python Code)

Max Activating Token Index: 424

Text #19

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4727. Min Act: -0.0001

Data Index: 1249206 (C4 (Web Text))

Max Activating Token Index: 529