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

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

Neuron 1959 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: 0.7953. Min Range: -0.7953

Max Act: 0.7953. Min Act: -0.0001

Data Index: 1241218 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.7494. Min Act: -0.0001

Data Index: 640395 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.7637. Min Act: -0.0001

Data Index: 265460 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.7444. Min Act: -0.0001

Data Index: 945610 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.7545. Min Act: -0.0001

Data Index: 848879 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.7164. Min Act: -0.0001

Data Index: 811892 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.7098. Min Act: -0.0001

Data Index: 1196622 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.7212. Min Act: -0.0001

Data Index: 845528 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6844. Min Act: -0.0001

Data Index: 22686 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6937. Min Act: -0.0001

Data Index: 711414 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6479. Min Act: -0.0001

Data Index: 968035 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6845. Min Act: -0.0001

Data Index: 742474 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6686. Min Act: -0.0001

Data Index: 1003732 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6200. Min Act: -0.0001

Data Index: 1310045 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6682. Min Act: -0.0001

Data Index: 1082515 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6282. Min Act: -0.0001

Data Index: 1337431 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6143. Min Act: -0.0001

Data Index: 106008 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6364. Min Act: -0.0001

Data Index: 1582372 (Python Code)

Max Activating Token Index: 610

Text #18

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6197. Min Act: -0.0001

Data Index: 415473 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6321. Min Act: -0.0001

Data Index: 179790 (C4 (Web Text))

Max Activating Token Index: 41