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

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

Neuron 3683 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3541. Min Act: -0.0001

Data Index: 867046 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3943. Min Act: -0.0001

Data Index: 214833 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3739. Min Act: -0.0001

Data Index: 390310 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3306. Min Act: -0.0001

Data Index: 633187 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2917. Min Act: -0.0001

Data Index: 286324 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2788. Min Act: -0.0001

Data Index: 399092 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3009. Min Act: -0.0001

Data Index: 429568 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2809. Min Act: -0.0001

Data Index: 465726 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2744. Min Act: -0.0001

Data Index: 772968 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2708. Min Act: -0.0001

Data Index: 821965 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2573. Min Act: -0.0001

Data Index: 206643 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2366. Min Act: -0.0001

Data Index: 498406 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2190. Min Act: -0.0001

Data Index: 71603 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2071. Min Act: -0.0001

Data Index: 1351336 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2018. Min Act: -0.0001

Data Index: 767523 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.1835. Min Act: -0.0001

Data Index: 617813 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.1924. Min Act: -0.0001

Data Index: 976260 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.1420. Min Act: -0.0001

Data Index: 571029 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.1743. Min Act: -0.0001

Data Index: 803877 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.1488. Min Act: -0.0001

Data Index: 322109 (C4 (Web Text))

Max Activating Token Index: 732