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

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

Neuron 3926 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: 2.3746. Min Range: -2.3746

Max Act: 2.3746. Min Act: -0.0000

Data Index: 927524 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 2.3746. Min Range: -2.3746

Max Act: 2.0084. Min Act: -0.0000

Data Index: 384871 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 2.3746. Min Range: -2.3746

Max Act: 2.1276. Min Act: -0.0000

Data Index: 1339800 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 2.3746. Min Range: -2.3746

Max Act: 2.0381. Min Act: -0.0000

Data Index: 689483 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.8671. Min Act: -0.0000

Data Index: 719277 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.9407. Min Act: -0.0000

Data Index: 1076567 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 2.3746. Min Range: -2.3746

Max Act: 2.0605. Min Act: -0.0000

Data Index: 858113 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.8334. Min Act: -0.0000

Data Index: 480210 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.7463. Min Act: -0.0000

Data Index: 173424 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.7893. Min Act: -0.0000

Data Index: 579347 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.7563. Min Act: -0.0000

Data Index: 582166 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.7366. Min Act: -0.0000

Data Index: 788239 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.5351. Min Act: -0.0000

Data Index: 203155 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.6959. Min Act: -0.0000

Data Index: 1200901 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.7258. Min Act: -0.0000

Data Index: 328222 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.7156. Min Act: -0.0000

Data Index: 1077746 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.6439. Min Act: -0.0000

Data Index: 874401 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.6413. Min Act: -0.0000

Data Index: 1349837 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.4262. Min Act: -0.0000

Data Index: 407571 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 2.3746. Min Range: -2.3746

Max Act: 1.4935. Min Act: -0.0000

Data Index: 425824 (C4 (Web Text))

Max Activating Token Index: 687