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

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

Neuron 3094 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3894. Min Range: -7.3894

Max Act: 7.3894. Min Act: -0.0001

Data Index: 482817 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 7.3894. Min Range: -7.3894

Max Act: 6.1699. Min Act: -0.0001

Data Index: 504070 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 7.3894. Min Range: -7.3894

Max Act: 6.0921. Min Act: -0.0000

Data Index: 1220403 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 7.3894. Min Range: -7.3894

Max Act: 6.2797. Min Act: -0.0001

Data Index: 847832 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 7.3894. Min Range: -7.3894

Max Act: 6.0533. Min Act: -0.0001

Data Index: 1262717 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 7.3894. Min Range: -7.3894

Max Act: 6.1147. Min Act: -0.0001

Data Index: 739427 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 7.3894. Min Range: -7.3894

Max Act: 6.0898. Min Act: -0.0001

Data Index: 986760 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 7.3894. Min Range: -7.3894

Max Act: 6.2443. Min Act: -0.0001

Data Index: 168436 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 7.3894. Min Range: -7.3894

Max Act: 6.1514. Min Act: -0.0001

Data Index: 593003 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.8965. Min Act: -0.0001

Data Index: 951412 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.6237. Min Act: -0.0001

Data Index: 245356 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.7752. Min Act: -0.0001

Data Index: 978714 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.5857. Min Act: -0.0001

Data Index: 318329 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 7.3894. Min Range: -7.3894

Max Act: 6.0489. Min Act: -0.0001

Data Index: 251372 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.9521. Min Act: -0.0001

Data Index: 53025 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.7346. Min Act: -0.0001

Data Index: 284562 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 7.3894. Min Range: -7.3894

Max Act: 6.1010. Min Act: -0.0001

Data Index: 960074 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.5477. Min Act: -0.0001

Data Index: 221833 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.5097. Min Act: -0.0001

Data Index: 1333232 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.4854. Min Act: -0.0001

Data Index: 84605 (C4 (Web Text))

Max Activating Token Index: 924