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

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

Neuron 4285 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: 1.3678. Min Range: -1.3678

Max Act: 1.2621. Min Act: -0.0000

Data Index: 485670 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.3411. Min Act: -0.0000

Data Index: 112534 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.1622. Min Act: -0.0000

Data Index: 347310 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1235766 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0686. Min Act: -0.0000

Data Index: 191014 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1176050 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9819. Min Act: -0.0000

Data Index: 840164 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1310620 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9583. Min Act: -0.0000

Data Index: 339302 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.8800. Min Act: -0.0000

Data Index: 407744 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.8220. Min Act: -0.0000

Data Index: 505821 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9357. Min Act: -0.0000

Data Index: 176891 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1122243 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1032550 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.8779. Min Act: -0.0000

Data Index: 159570 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.8455. Min Act: -0.0000

Data Index: 54527 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.7717. Min Act: -0.0000

Data Index: 982000 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.7966. Min Act: -0.0000

Data Index: 173602 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.8450. Min Act: -0.0000

Data Index: 179025 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.8433. Min Act: -0.0000

Data Index: 996820 (C4 (Web Text))

Max Activating Token Index: 245