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

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

Neuron 4190 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0511. Min Range: -3.0511

Max Act: 3.0511. Min Act: -0.0000

Data Index: 590381 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 3.0511. Min Range: -3.0511

Max Act: 2.2096. Min Act: -0.0000

Data Index: 928924 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 3.0511. Min Range: -3.0511

Max Act: 2.0937. Min Act: -0.0000

Data Index: 518214 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.9360. Min Act: -0.0000

Data Index: 1032819 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 3.0511. Min Range: -3.0511

Max Act: 2.0218. Min Act: -0.0000

Data Index: 419444 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.7598. Min Act: -0.0000

Data Index: 975020 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.8460. Min Act: -0.0000

Data Index: 741016 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.8141. Min Act: -0.0000

Data Index: 160149 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.7523. Min Act: -0.0000

Data Index: 1055935 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.7315. Min Act: -0.0000

Data Index: 393100 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.6387. Min Act: -0.0000

Data Index: 50000 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.7175. Min Act: -0.0000

Data Index: 238161 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.7180. Min Act: -0.0000

Data Index: 594345 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.7057. Min Act: -0.0000

Data Index: 769714 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.6210. Min Act: -0.0000

Data Index: 996148 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.6003. Min Act: -0.0000

Data Index: 542787 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.5090. Min Act: -0.0000

Data Index: 343895 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.5441. Min Act: -0.0000

Data Index: 62888 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.5333. Min Act: -0.0000

Data Index: 149988 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 3.0511. Min Range: -3.0511

Max Act: 1.6009. Min Act: -0.0000

Data Index: 101100 (C4 (Web Text))

Max Activating Token Index: 801