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

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

Neuron 1682 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1312. Min Range: -2.1312

Max Act: 2.1312. Min Act: -0.0000

Data Index: 438308 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 2.1312. Min Range: -2.1312

Max Act: 2.0346. Min Act: -0.0000

Data Index: 1239575 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.8175. Min Act: -0.0000

Data Index: 221465 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7960. Min Act: -0.0000

Data Index: 1105506 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7790. Min Act: -0.0000

Data Index: 726407 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.9129. Min Act: -0.0000

Data Index: 623586 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7078. Min Act: -0.0000

Data Index: 736795 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6455. Min Act: -0.0001

Data Index: 698324 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7752. Min Act: -0.0000

Data Index: 1146109 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6177. Min Act: -0.0000

Data Index: 275231 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6720. Min Act: -0.0000

Data Index: 249054 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7000. Min Act: -0.0001

Data Index: 915974 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6153. Min Act: -0.0000

Data Index: 199237 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7672. Min Act: -0.0001

Data Index: 452496 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.5059. Min Act: -0.0000

Data Index: 1287610 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6343. Min Act: -0.0000

Data Index: 705220 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.5874. Min Act: -0.0000

Data Index: 1105863 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.5862. Min Act: -0.0000

Data Index: 150091 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6194. Min Act: -0.0000

Data Index: 1261835 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6256. Min Act: -0.0000

Data Index: 1110650 (C4 (Web Text))

Max Activating Token Index: 708