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

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

Neuron 5636 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.7534. Min Act: -0.0000

Data Index: 1092147 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.6114. Min Act: -0.0000

Data Index: 1019133 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.5998. Min Act: -0.0000

Data Index: 258788 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.7862. Min Act: -0.0000

Data Index: 1589608 (Python Code)

Max Activating Token Index: 266

Text #4

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.4298. Min Act: -0.0000

Data Index: 1401099 (Python Code)

Max Activating Token Index: 401

Text #5

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.4197. Min Act: -0.0000

Data Index: 238460 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.3906. Min Act: -0.0000

Data Index: 255533 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.2158. Min Act: -0.0000

Data Index: 754253 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.1840. Min Act: -0.0000

Data Index: 355272 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.3399. Min Act: -0.0000

Data Index: 1358360 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.1754. Min Act: -0.0000

Data Index: 1227765 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.0166. Min Act: -0.0000

Data Index: 929743 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.0917. Min Act: -0.0000

Data Index: 653138 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 3.7862. Min Range: -3.7862

Max Act: 2.9278. Min Act: -0.0000

Data Index: 840958 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 3.7862. Min Range: -3.7862

Max Act: 2.9215. Min Act: -0.0000

Data Index: 964438 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.1886. Min Act: -0.0000

Data Index: 710401 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.0018. Min Act: -0.0000

Data Index: 1101346 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 3.7862. Min Range: -3.7862

Max Act: 3.1434. Min Act: -0.0000

Data Index: 736869 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 3.7862. Min Range: -3.7862

Max Act: 2.8456. Min Act: -0.0000

Data Index: 602889 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 3.7862. Min Range: -3.7862

Max Act: 2.9604. Min Act: -0.0000

Data Index: 603880 (C4 (Web Text))

Max Activating Token Index: 102