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

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

Neuron 2470 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: 0.3491. Min Range: -0.3491

Max Act: 0.3491. Min Act: -0.0000

Data Index: 317264 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2969. Min Act: -0.0000

Data Index: 505668 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3216. Min Act: -0.0000

Data Index: 341205 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2900. Min Act: -0.0000

Data Index: 334607 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1467345 (Python Code)

Max Activating Token Index: 137

Text #5

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2971. Min Act: -0.0000

Data Index: 560401 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1530578 (Python Code)

Max Activating Token Index: 73

Text #7

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2378. Min Act: -0.0000

Data Index: 834393 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2883. Min Act: -0.0000

Data Index: 324242 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1371846 (Python Code)

Max Activating Token Index: 720

Text #10

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1603389 (Python Code)

Max Activating Token Index: 565

Text #11

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1473723 (Python Code)

Max Activating Token Index: 945

Text #12

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2690. Min Act: -0.0000

Data Index: 612222 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2732. Min Act: -0.0000

Data Index: 363098 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2652. Min Act: -0.0000

Data Index: 607218 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2618. Min Act: -0.0000

Data Index: 290691 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1060757 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2541. Min Act: -0.0000

Data Index: 49234 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2543. Min Act: -0.0000

Data Index: 868528 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1214021 (C4 (Web Text))

Max Activating Token Index: 909