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

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

Neuron 4398 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.8470. Min Act: -0.0000

Data Index: 1454309 (Python Code)

Max Activating Token Index: 873

Text #1

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.5624. Min Act: -0.0000

Data Index: 1400685 (Python Code)

Max Activating Token Index: 853

Text #2

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.3240. Min Act: -0.0000

Data Index: 1442484 (Python Code)

Max Activating Token Index: 815

Text #3

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.3171. Min Act: -0.0000

Data Index: 1465790 (Python Code)

Max Activating Token Index: 602

Text #4

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.3059. Min Act: -0.0000

Data Index: 1459392 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1622457 (Python Code)

Max Activating Token Index: 304

Text #6

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.2889. Min Act: -0.0000

Data Index: 1469268 (Python Code)

Max Activating Token Index: 877

Text #7

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.2688. Min Act: -0.0000

Data Index: 1570620 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.1433. Min Act: -0.0000

Data Index: 1535591 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.1303. Min Act: -0.0000

Data Index: 904492 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1449099 (Python Code)

Max Activating Token Index: 645

Text #11

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.1229. Min Act: -0.0000

Data Index: 868090 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.1200. Min Act: -0.0000

Data Index: 1443806 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.1075. Min Act: -0.0000

Data Index: 1402589 (Python Code)

Max Activating Token Index: 251

Text #14

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.0847. Min Act: -0.0000

Data Index: 784166 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1598432 (Python Code)

Max Activating Token Index: 351

Text #16

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.0064. Min Act: -0.0000

Data Index: 1614305 (Python Code)

Max Activating Token Index: 588

Text #17

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.0589. Min Act: -0.0000

Data Index: 1591099 (Python Code)

Max Activating Token Index: 198

Text #18

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.1254. Min Act: -0.0000

Data Index: 1151571 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1415468 (Python Code)

Max Activating Token Index: 520