Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1785 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4149. Min Range: -3.4149

Max Act: 3.4149. Min Act: -0.0000

Data Index: 783800 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.4149. Min Range: -3.4149

Max Act: 3.1277. Min Act: -0.0000

Data Index: 346270 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 3.4149. Min Range: -3.4149

Max Act: 3.0450. Min Act: -0.0000

Data Index: 536252 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.8768. Min Act: -0.0000

Data Index: 52385 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.8235. Min Act: -0.0000

Data Index: 975278 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.6325. Min Act: -0.0000

Data Index: 659660 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.5034. Min Act: -0.0000

Data Index: 819529 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.6180. Min Act: -0.0000

Data Index: 531752 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.4840. Min Act: -0.0000

Data Index: 7568 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.6007. Min Act: -0.0000

Data Index: 40965 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.3401. Min Act: -0.0000

Data Index: 1056031 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.5539. Min Act: -0.0000

Data Index: 38833 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.5451. Min Act: -0.0000

Data Index: 393321 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.3796. Min Act: -0.0000

Data Index: 700928 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.3470. Min Act: -0.0000

Data Index: 960720 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.3380. Min Act: -0.0000

Data Index: 1138776 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.3199. Min Act: -0.0000

Data Index: 408332 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.2519. Min Act: -0.0000

Data Index: 809752 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.2864. Min Act: -0.0000

Data Index: 1185027 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 3.4149. Min Range: -3.4149

Max Act: 2.2799. Min Act: -0.0000

Data Index: 1078945 (C4 (Web Text))

Max Activating Token Index: 643