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

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

Neuron 3409 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: 0.4137. Min Range: -0.4137

Max Act: 0.4137. Min Act: -0.0000

Data Index: 204899 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3109. Min Act: 0.0000

Data Index: 302069 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3009. Min Act: -0.0000

Data Index: 795799 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3046. Min Act: -0.0000

Data Index: 716458 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2884. Min Act: -0.0000

Data Index: 51075 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2844. Min Act: -0.0000

Data Index: 454305 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2928. Min Act: -0.0000

Data Index: 131065 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2682. Min Act: -0.0000

Data Index: 121514 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1323060 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2532. Min Act: -0.0000

Data Index: 167392 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2323. Min Act: -0.0000

Data Index: 440456 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2551. Min Act: 0.0000

Data Index: 1156184 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2414. Min Act: -0.0000

Data Index: 602106 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2507. Min Act: -0.0000

Data Index: 643674 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2442. Min Act: -0.0000

Data Index: 920424 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2491. Min Act: -0.0000

Data Index: 389948 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2289. Min Act: -0.0000

Data Index: 891159 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1075895 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2466. Min Act: -0.0000

Data Index: 355276 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2219. Min Act: -0.0000

Data Index: 362623 (C4 (Web Text))

Max Activating Token Index: 201