Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3796 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5933. Min Act: -0.0000

Data Index: 435657 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5629. Min Act: -0.0000

Data Index: 492233 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5550. Min Act: -0.0000

Data Index: 1281013 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5601. Min Act: -0.0000

Data Index: 1053161 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.3717. Min Act: -0.0000

Data Index: 777669 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.4499. Min Act: -0.0000

Data Index: 4784 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.4686. Min Act: -0.0000

Data Index: 1328095 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5381. Min Act: -0.0000

Data Index: 556943 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.4325. Min Act: -0.0000

Data Index: 135150 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.3475. Min Act: -0.0001

Data Index: 1103300 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.4030. Min Act: -0.0000

Data Index: 811058 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5380. Min Act: -0.0000

Data Index: 595290 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.3805. Min Act: -0.0000

Data Index: 938447 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.3256. Min Act: -0.0000

Data Index: 782674 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.3251. Min Act: -0.0000

Data Index: 383379 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.2669. Min Act: -0.0000

Data Index: 794753 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.2011. Min Act: -0.0000

Data Index: 240057 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1670. Min Act: -0.0000

Data Index: 837038 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.2612. Min Act: -0.0000

Data Index: 654427 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.2830. Min Act: -0.0000

Data Index: 1358804 (C4 (Web Text))

Max Activating Token Index: 293