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

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

Neuron 4475 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1416603 (Python Code)

Max Activating Token Index: 972

Text #1

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1643141 (Python Code)

Max Activating Token Index: 887

Text #2

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3244. Min Act: -0.0000

Data Index: 1544178 (Python Code)

Max Activating Token Index: 701

Text #3

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1412250 (Python Code)

Max Activating Token Index: 724

Text #4

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1465911 (Python Code)

Max Activating Token Index: 31

Text #5

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1609180 (Python Code)

Max Activating Token Index: 69

Text #6

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1562731 (Python Code)

Max Activating Token Index: 486

Text #7

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1057235 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1500281 (Python Code)

Max Activating Token Index: 730

Text #9

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1577217 (Python Code)

Max Activating Token Index: 167

Text #10

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1436781 (Python Code)

Max Activating Token Index: 854

Text #11

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1545923 (Python Code)

Max Activating Token Index: 466

Text #12

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1391712 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2806. Min Act: -0.0000

Data Index: 1506817 (Python Code)

Max Activating Token Index: 918

Text #14

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1057533 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1083678 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1533631 (Python Code)

Max Activating Token Index: 325

Text #17

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2613. Min Act: 0.0000

Data Index: 1124653 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1491627 (Python Code)

Max Activating Token Index: 495

Text #19

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1475420 (Python Code)

Max Activating Token Index: 46