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

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

Neuron 841 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1539384 (Python Code)

Max Activating Token Index: 110

Text #1

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1574189 (Python Code)

Max Activating Token Index: 500

Text #2

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1397758 (Python Code)

Max Activating Token Index: 213

Text #3

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1509697 (Python Code)

Max Activating Token Index: 176

Text #4

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3003. Min Act: -0.0000

Data Index: 590924 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1364757 (Python Code)

Max Activating Token Index: 78

Text #6

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2774. Min Act: -0.0000

Data Index: 899260 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1520649 (Python Code)

Max Activating Token Index: 72

Text #8

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1404260 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2637. Min Act: -0.0000

Data Index: 758974 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1385910 (Python Code)

Max Activating Token Index: 36

Text #11

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1113753 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1513828 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1523119 (Python Code)

Max Activating Token Index: 268

Text #14

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2459. Min Act: -0.0001

Data Index: 1613312 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2407. Min Act: -0.0000

Data Index: 227430 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2484. Min Act: -0.0000

Data Index: 427914 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1056351 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1444317 (Python Code)

Max Activating Token Index: 369

Text #19

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2286. Min Act: -0.0000

Data Index: 742190 (C4 (Web Text))

Max Activating Token Index: 677