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

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

Neuron 2392 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4118. Min Range: -2.4118

Max Act: 2.4118. Min Act: -0.0000

Data Index: 130648 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 2.4118. Min Range: -2.4118

Max Act: 2.1471. Min Act: -0.0000

Data Index: 1033823 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 2.4118. Min Range: -2.4118

Max Act: 2.1402. Min Act: -0.0000

Data Index: 562908 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 2.4118. Min Range: -2.4118

Max Act: 2.0599. Min Act: -0.0000

Data Index: 929420 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 2.4118. Min Range: -2.4118

Max Act: 1.9462. Min Act: -0.0000

Data Index: 6279 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 2.4118. Min Range: -2.4118

Max Act: 2.0218. Min Act: -0.0000

Data Index: 1229189 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 2.4118. Min Range: -2.4118

Max Act: 1.9552. Min Act: -0.0000

Data Index: 527087 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 2.4118. Min Range: -2.4118

Max Act: 2.0454. Min Act: -0.0000

Data Index: 86796 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 2.4118. Min Range: -2.4118

Max Act: 2.0414. Min Act: -0.0000

Data Index: 766922 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 2.4118. Min Range: -2.4118

Max Act: 1.8260. Min Act: -0.0000

Data Index: 594888 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 2.4118. Min Range: -2.4118

Max Act: 1.9309. Min Act: -0.0000

Data Index: 529498 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 2.4118. Min Range: -2.4118

Max Act: 1.8288. Min Act: -0.0000

Data Index: 1180532 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 2.4118. Min Range: -2.4118

Max Act: 1.8421. Min Act: -0.0000

Data Index: 752854 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 2.4118. Min Range: -2.4118

Max Act: 1.7311. Min Act: -0.0000

Data Index: 642779 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 2.4118. Min Range: -2.4118

Max Act: 1.8037. Min Act: -0.0000

Data Index: 1174702 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 2.4118. Min Range: -2.4118

Max Act: 1.7857. Min Act: -0.0000

Data Index: 757375 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 2.4118. Min Range: -2.4118

Max Act: 1.8005. Min Act: -0.0000

Data Index: 927742 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 2.4118. Min Range: -2.4118

Max Act: 1.7619. Min Act: -0.0000

Data Index: 810146 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 2.4118. Min Range: -2.4118

Max Act: 1.7533. Min Act: -0.0000

Data Index: 492776 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 2.4118. Min Range: -2.4118

Max Act: 1.7587. Min Act: -0.0000

Data Index: 781296 (C4 (Web Text))

Max Activating Token Index: 164