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

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

Neuron 1588 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3908. Min Range: -4.3908

Max Act: 4.1486. Min Act: -0.0001

Data Index: 1301763 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.9706. Min Act: -0.0001

Data Index: 268669 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 4.3908. Min Range: -4.3908

Max Act: 4.3908. Min Act: -0.0001

Data Index: 1012899 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 4.3908. Min Range: -4.3908

Max Act: 4.0430. Min Act: -0.0001

Data Index: 993199 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.9375. Min Act: -0.0001

Data Index: 1261131 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.9010. Min Act: -0.0001

Data Index: 1169186 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.9407. Min Act: -0.0001

Data Index: 735026 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.7682. Min Act: -0.0001

Data Index: 1258333 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.4184. Min Act: -0.0000

Data Index: 381564 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.5567. Min Act: -0.0001

Data Index: 1241421 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.4036. Min Act: -0.0001

Data Index: 268260 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.2290. Min Act: -0.0000

Data Index: 1623917 (Python Code)

Max Activating Token Index: 54

Text #12

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.0517. Min Act: -0.0001

Data Index: 1455541 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.1699. Min Act: -0.0000

Data Index: 1385628 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 4.3908. Min Range: -4.3908

Max Act: 2.7276. Min Act: -0.0001

Data Index: 1508474 (Python Code)

Max Activating Token Index: 171

Text #15

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.2821. Min Act: -0.0001

Data Index: 929402 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 4.3908. Min Range: -4.3908

Max Act: 2.8183. Min Act: -0.0001

Data Index: 846079 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 4.3908. Min Range: -4.3908

Max Act: 2.9091. Min Act: -0.0001

Data Index: 1381462 (Python Code)

Max Activating Token Index: 275

Text #18

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.1494. Min Act: -0.0001

Data Index: 541319 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 4.3908. Min Range: -4.3908

Max Act: 3.1830. Min Act: -0.0001

Data Index: 1613971 (Python Code)

Max Activating Token Index: 71