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

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

Neuron 3948 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3632. Min Range: -2.3632

Max Act: 2.3632. Min Act: -0.0000

Data Index: 421320 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.7918. Min Act: -0.0000

Data Index: 1094949 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.7255. Min Act: -0.0000

Data Index: 529209 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.5970. Min Act: -0.0000

Data Index: 1194510 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.5239. Min Act: -0.0000

Data Index: 1080444 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.5058. Min Act: -0.0001

Data Index: 199886 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.4641. Min Act: -0.0000

Data Index: 1489861 (Python Code)

Max Activating Token Index: 149

Text #7

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.4898. Min Act: -0.0001

Data Index: 552744 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.4241. Min Act: -0.0000

Data Index: 198226 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.3746. Min Act: -0.0001

Data Index: 1023439 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.3247. Min Act: -0.0000

Data Index: 1298020 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.2600. Min Act: -0.0000

Data Index: 1243707 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.3340. Min Act: -0.0000

Data Index: 151113 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.3303. Min Act: -0.0000

Data Index: 351840 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.2678. Min Act: -0.0000

Data Index: 461151 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.2639. Min Act: -0.0000

Data Index: 632699 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.2087. Min Act: -0.0000

Data Index: 243982 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.1134. Min Act: -0.0000

Data Index: 1445419 (Python Code)

Max Activating Token Index: 808

Text #18

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1243929 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 2.3632. Min Range: -2.3632

Max Act: 1.2420. Min Act: -0.0000

Data Index: 721320 (C4 (Web Text))

Max Activating Token Index: 41