Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 458 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3596. Min Act: -0.0000

Data Index: 93333 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3322. Min Act: -0.0000

Data Index: 701472 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3117. Min Act: -0.0000

Data Index: 639223 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3146. Min Act: -0.0000

Data Index: 344606 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2852. Min Act: -0.0000

Data Index: 168364 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3048. Min Act: -0.0001

Data Index: 863846 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2944. Min Act: -0.0000

Data Index: 615239 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2832. Min Act: -0.0001

Data Index: 715833 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1186961 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2794. Min Act: -0.0001

Data Index: 921444 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2748. Min Act: -0.0000

Data Index: 723104 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1101163 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2705. Min Act: -0.0000

Data Index: 45600 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2786. Min Act: -0.0000

Data Index: 454491 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2686. Min Act: 0.0000

Data Index: 739614 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2679. Min Act: 0.0000

Data Index: 1287276 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2516. Min Act: -0.0000

Data Index: 716534 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1010132 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1192439 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2644. Min Act: -0.0001

Data Index: 779799 (C4 (Web Text))

Max Activating Token Index: 177