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

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

Neuron 4750 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6699. Min Range: -2.6699

Max Act: 2.6699. Min Act: -0.0000

Data Index: 102925 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.8897. Min Act: -0.0000

Data Index: 1281848 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.7613. Min Act: -0.0000

Data Index: 220021 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.8342. Min Act: -0.0000

Data Index: 223469 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.7047. Min Act: -0.0000

Data Index: 539590 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.4777. Min Act: -0.0000

Data Index: 1010508 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.4607. Min Act: -0.0000

Data Index: 103373 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.3191. Min Act: -0.0000

Data Index: 897625 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.3099. Min Act: -0.0000

Data Index: 225152 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.3272. Min Act: -0.0000

Data Index: 680225 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.3557. Min Act: -0.0000

Data Index: 1490183 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.2625. Min Act: -0.0000

Data Index: 764220 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.3712. Min Act: -0.0000

Data Index: 977644 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.3726. Min Act: -0.0000

Data Index: 1230525 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.2838. Min Act: -0.0000

Data Index: 207200 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.2777. Min Act: -0.0000

Data Index: 1646881 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.3039. Min Act: -0.0000

Data Index: 1399779 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.2787. Min Act: -0.0000

Data Index: 273450 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.3286. Min Act: -0.0000

Data Index: 1061608 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 2.6699. Min Range: -2.6699

Max Act: 1.1254. Min Act: -0.0000

Data Index: 293222 (C4 (Web Text))

Max Activating Token Index: 105