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

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

Neuron 3127 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.6112. Min Act: -0.0000

Data Index: 1032266 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.3598. Min Act: -0.0000

Data Index: 1000656 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.3725. Min Act: -0.0000

Data Index: 128324 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.3882. Min Act: -0.0000

Data Index: 1163431 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.2323. Min Act: -0.0000

Data Index: 621043 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.3288. Min Act: -0.0000

Data Index: 70467 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.0568. Min Act: -0.0000

Data Index: 39860 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.1736. Min Act: -0.0000

Data Index: 221319 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.2572. Min Act: -0.0000

Data Index: 660071 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 2.6112. Min Range: -2.6112

Max Act: 1.9150. Min Act: -0.0000

Data Index: 268481 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.1231. Min Act: -0.0000

Data Index: 928514 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.1019. Min Act: -0.0000

Data Index: 1128836 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.1565. Min Act: -0.0000

Data Index: 554851 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.0848. Min Act: -0.0000

Data Index: 412672 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.0809. Min Act: -0.0000

Data Index: 930527 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.0754. Min Act: -0.0000

Data Index: 1189221 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.0670. Min Act: -0.0000

Data Index: 803482 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.1802. Min Act: -0.0000

Data Index: 508702 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.1666. Min Act: -0.0000

Data Index: 676617 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 2.6112. Min Range: -2.6112

Max Act: 2.0246. Min Act: -0.0000

Data Index: 751923 (C4 (Web Text))

Max Activating Token Index: 85