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

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

Neuron 1028 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1359071 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2618. Min Act: -0.0000

Data Index: 729401 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2720. Min Act: -0.0000

Data Index: 264070 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2637. Min Act: -0.0000

Data Index: 504346 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1751. Min Act: -0.0000

Data Index: 43811 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1324. Min Act: -0.0000

Data Index: 1044661 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1940. Min Act: -0.0000

Data Index: 376700 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1554. Min Act: -0.0000

Data Index: 432423 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1060795 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1145. Min Act: -0.0000

Data Index: 941951 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1172. Min Act: -0.0000

Data Index: 809431 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1061. Min Act: -0.0000

Data Index: 241728 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0310. Min Act: -0.0000

Data Index: 653661 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0832. Min Act: -0.0000

Data Index: 989203 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0841. Min Act: -0.0000

Data Index: 296640 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0723. Min Act: -0.0000

Data Index: 899110 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0722. Min Act: -0.0000

Data Index: 1231409 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0607. Min Act: -0.0000

Data Index: 75433 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0939. Min Act: -0.0000

Data Index: 140411 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0276. Min Act: -0.0000

Data Index: 177048 (C4 (Web Text))

Max Activating Token Index: 510