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

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

Neuron 4589 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: 4.4191. Min Range: -4.4191

Max Act: 4.4191. Min Act: -0.0000

Data Index: 476620 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.9083. Min Act: -0.0000

Data Index: 237298 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.9719. Min Act: -0.0000

Data Index: 154125 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.3244. Min Act: -0.0000

Data Index: 448976 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.2891. Min Act: -0.0000

Data Index: 770890 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.4349. Min Act: -0.0000

Data Index: 1104160 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.4168. Min Act: -0.0000

Data Index: 426234 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.3814. Min Act: -0.0000

Data Index: 111517 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.3542. Min Act: -0.0000

Data Index: 349574 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.1243. Min Act: -0.0000

Data Index: 833334 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.4131. Min Act: -0.0000

Data Index: 1248795 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.0725. Min Act: -0.0000

Data Index: 526141 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.0191. Min Act: -0.0000

Data Index: 750726 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.1487. Min Act: -0.0000

Data Index: 760018 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.1217. Min Act: -0.0000

Data Index: 151557 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 4.4191. Min Range: -4.4191

Max Act: 2.8009. Min Act: -0.0000

Data Index: 990622 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 4.4191. Min Range: -4.4191

Max Act: 2.9168. Min Act: -0.0000

Data Index: 312546 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.0321. Min Act: -0.0000

Data Index: 1110344 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 4.4191. Min Range: -4.4191

Max Act: 3.0210. Min Act: -0.0000

Data Index: 141780 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 4.4191. Min Range: -4.4191

Max Act: 2.8713. Min Act: -0.0000

Data Index: 355970 (C4 (Web Text))

Max Activating Token Index: 530