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

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

Neuron 5063 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.7086. Min Act: -0.0001

Data Index: 1574635 (Python Code)

Max Activating Token Index: 585

Text #1

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.7284. Min Act: -0.0001

Data Index: 1010756 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.7274. Min Act: -0.0001

Data Index: 889356 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.7277. Min Act: -0.0001

Data Index: 703598 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.7102. Min Act: -0.0001

Data Index: 1330231 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.6986. Min Act: -0.0001

Data Index: 70441 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.6937. Min Act: -0.0001

Data Index: 1204205 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.7110. Min Act: -0.0001

Data Index: 1315774 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.6851. Min Act: -0.0001

Data Index: 1015858 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.6374. Min Act: -0.0001

Data Index: 367209 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.6437. Min Act: -0.0001

Data Index: 2746 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.6549. Min Act: -0.0001

Data Index: 1087153 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.6532. Min Act: -0.0001

Data Index: 480572 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.6268. Min Act: -0.0001

Data Index: 45132 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.6823. Min Act: -0.0001

Data Index: 113615 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.6266. Min Act: -0.0001

Data Index: 723138 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.6466. Min Act: -0.0001

Data Index: 1103281 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.6314. Min Act: -0.0001

Data Index: 258758 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.6456. Min Act: -0.0001

Data Index: 135962 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.7284. Min Range: -0.7284

Max Act: 0.5958. Min Act: -0.0001

Data Index: 73390 (C4 (Web Text))

Max Activating Token Index: 755