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

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

Neuron 40 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: 0.6876. Min Range: -0.6876

Max Act: 0.6876. Min Act: -0.0001

Data Index: 301435 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5343. Min Act: -0.0000

Data Index: 1315889 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5477. Min Act: -0.0000

Data Index: 144738 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5114. Min Act: -0.0000

Data Index: 509233 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5085. Min Act: -0.0000

Data Index: 255140 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4896. Min Act: -0.0000

Data Index: 711619 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5188. Min Act: -0.0000

Data Index: 446181 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5081. Min Act: -0.0000

Data Index: 845291 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4750. Min Act: -0.0000

Data Index: 652401 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4840. Min Act: -0.0000

Data Index: 901164 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4763. Min Act: -0.0000

Data Index: 390881 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4664. Min Act: -0.0000

Data Index: 721815 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4599. Min Act: -0.0000

Data Index: 267515 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4418. Min Act: -0.0000

Data Index: 958599 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4234. Min Act: -0.0000

Data Index: 385289 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4384. Min Act: -0.0000

Data Index: 806180 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1079727 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4468. Min Act: -0.0000

Data Index: 287756 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.3999. Min Act: -0.0000

Data Index: 665237 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4534. Min Act: -0.0001

Data Index: 25753 (C4 (Web Text))

Max Activating Token Index: 30