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

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

Neuron 1998 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5429. Min Range: -3.5429

Max Act: 3.5429. Min Act: -0.0000

Data Index: 1183331 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.7640. Min Act: -0.0000

Data Index: 557169 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.6909. Min Act: -0.0000

Data Index: 885680 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.4601. Min Act: -0.0000

Data Index: 924478 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.2005. Min Act: -0.0000

Data Index: 966586 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.3261. Min Act: -0.0000

Data Index: 74077 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.0929. Min Act: -0.0000

Data Index: 994143 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 3.5429. Min Range: -3.5429

Max Act: 1.9334. Min Act: -0.0000

Data Index: 494743 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 3.5429. Min Range: -3.5429

Max Act: 1.8438. Min Act: -0.0000

Data Index: 1004701 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 3.5429. Min Range: -3.5429

Max Act: 2.0365. Min Act: -0.0000

Data Index: 592300 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 3.5429. Min Range: -3.5429

Max Act: 1.9216. Min Act: -0.0000

Data Index: 1344460 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 3.5429. Min Range: -3.5429

Max Act: 1.9108. Min Act: -0.0000

Data Index: 658776 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 3.5429. Min Range: -3.5429

Max Act: 1.8840. Min Act: -0.0000

Data Index: 874589 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 3.5429. Min Range: -3.5429

Max Act: 1.9872. Min Act: -0.0000

Data Index: 681759 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 3.5429. Min Range: -3.5429

Max Act: 1.8725. Min Act: -0.0000

Data Index: 1058016 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 3.5429. Min Range: -3.5429

Max Act: 1.7612. Min Act: -0.0000

Data Index: 686773 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 3.5429. Min Range: -3.5429

Max Act: 1.8353. Min Act: -0.0000

Data Index: 390498 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 3.5429. Min Range: -3.5429

Max Act: 1.7207. Min Act: -0.0000

Data Index: 224199 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 3.5429. Min Range: -3.5429

Max Act: 1.6335. Min Act: -0.0000

Data Index: 491869 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 3.5429. Min Range: -3.5429

Max Act: 1.6564. Min Act: -0.0000

Data Index: 1340655 (C4 (Web Text))

Max Activating Token Index: 181