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

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

Neuron 4378 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2002. Min Act: -0.0000

Data Index: 943209 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2179. Min Act: -0.0000

Data Index: 378938 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1572. Min Act: -0.0000

Data Index: 202642 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2727. Min Act: -0.0000

Data Index: 362402 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2191. Min Act: -0.0000

Data Index: 481390 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1984. Min Act: -0.0000

Data Index: 471062 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2392. Min Act: -0.0000

Data Index: 836947 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 3.2727. Min Range: -3.2727

Max Act: 2.8908. Min Act: -0.0000

Data Index: 182688 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.0133. Min Act: -0.0000

Data Index: 331603 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 3.2727. Min Range: -3.2727

Max Act: 2.8306. Min Act: -0.0000

Data Index: 1028458 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 3.2727. Min Range: -3.2727

Max Act: 2.8601. Min Act: -0.0000

Data Index: 858359 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 3.2727. Min Range: -3.2727

Max Act: 2.9831. Min Act: -0.0000

Data Index: 461116 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 3.2727. Min Range: -3.2727

Max Act: 2.9130. Min Act: -0.0000

Data Index: 713810 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.0196. Min Act: -0.0000

Data Index: 192993 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 3.2727. Min Range: -3.2727

Max Act: 2.8853. Min Act: -0.0000

Data Index: 160649 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 3.2727. Min Range: -3.2727

Max Act: 2.6040. Min Act: -0.0000

Data Index: 1080409 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 3.2727. Min Range: -3.2727

Max Act: 2.7308. Min Act: -0.0000

Data Index: 20050 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 3.2727. Min Range: -3.2727

Max Act: 2.8589. Min Act: -0.0000

Data Index: 1205932 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 3.2727. Min Range: -3.2727

Max Act: 2.6830. Min Act: -0.0000

Data Index: 1191747 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 3.2727. Min Range: -3.2727

Max Act: 2.7907. Min Act: -0.0000

Data Index: 741932 (C4 (Web Text))

Max Activating Token Index: 609