Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5515 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4695. Min Range: -2.4695

Max Act: 2.4695. Min Act: -0.0000

Data Index: 105737 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 2.4695. Min Range: -2.4695

Max Act: 2.0360. Min Act: -0.0000

Data Index: 838637 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.7784. Min Act: -0.0000

Data Index: 187905 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.7675. Min Act: -0.0000

Data Index: 1270530 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.6808. Min Act: -0.0000

Data Index: 513162 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.8630. Min Act: -0.0000

Data Index: 988685 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.6574. Min Act: -0.0000

Data Index: 577522 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.4780. Min Act: -0.0000

Data Index: 1331684 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.4955. Min Act: -0.0001

Data Index: 1327035 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.3333. Min Act: -0.0000

Data Index: 1141650 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.4569. Min Act: -0.0000

Data Index: 219580 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.3959. Min Act: -0.0000

Data Index: 479174 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.2508. Min Act: -0.0000

Data Index: 81123 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.2179. Min Act: -0.0000

Data Index: 1261311 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.2933. Min Act: -0.0000

Data Index: 517728 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.3469. Min Act: -0.0000

Data Index: 507828 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.1412. Min Act: -0.0000

Data Index: 1269338 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.3217. Min Act: -0.0000

Data Index: 520124 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.2853. Min Act: -0.0000

Data Index: 1119816 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 2.4695. Min Range: -2.4695

Max Act: 1.2586. Min Act: -0.0000

Data Index: 672324 (C4 (Web Text))

Max Activating Token Index: 684