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

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

Neuron 535 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.9664. Min Act: -0.0001

Data Index: 800966 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.9385. Min Act: -0.0001

Data Index: 83664 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.8476. Min Act: -0.0001

Data Index: 676268 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.7957. Min Act: -0.0001

Data Index: 459720 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.8405. Min Act: -0.0001

Data Index: 54285 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.8049. Min Act: -0.0001

Data Index: 554853 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.7827. Min Act: -0.0001

Data Index: 1277246 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.7267. Min Act: -0.0001

Data Index: 126308 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.7971. Min Act: -0.0001

Data Index: 709494 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.7688. Min Act: -0.0001

Data Index: 578870 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.7407. Min Act: -0.0001

Data Index: 1128613 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.7547. Min Act: -0.0001

Data Index: 915199 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.7392. Min Act: -0.0001

Data Index: 686356 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.6968. Min Act: -0.0001

Data Index: 68545 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.7084. Min Act: -0.0001

Data Index: 882842 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.7008. Min Act: -0.0001

Data Index: 478744 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.7164. Min Act: -0.0001

Data Index: 1147860 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.6893. Min Act: -0.0001

Data Index: 186267 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.7030. Min Act: -0.0001

Data Index: 1133203 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.7005. Min Act: -0.0001

Data Index: 103752 (C4 (Web Text))

Max Activating Token Index: 21