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

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

Neuron 3054 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: 2.5465. Min Range: -2.5465

Max Act: 2.2645. Min Act: -0.0001

Data Index: 352802 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 2.5465. Min Range: -2.5465

Max Act: 2.5465. Min Act: -0.0000

Data Index: 1178209 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 2.5465. Min Range: -2.5465

Max Act: 2.2439. Min Act: -0.0001

Data Index: 608939 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 2.5465. Min Range: -2.5465

Max Act: 2.1040. Min Act: -0.0000

Data Index: 994592 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 2.5465. Min Range: -2.5465

Max Act: 2.2125. Min Act: -0.0001

Data Index: 1351737 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 2.5465. Min Range: -2.5465

Max Act: 2.0293. Min Act: -0.0000

Data Index: 394503 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 2.5465. Min Range: -2.5465

Max Act: 1.9456. Min Act: -0.0001

Data Index: 24077 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 2.5465. Min Range: -2.5465

Max Act: 1.9151. Min Act: -0.0000

Data Index: 197646 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 2.5465. Min Range: -2.5465

Max Act: 1.9378. Min Act: -0.0000

Data Index: 1108154 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 2.5465. Min Range: -2.5465

Max Act: 1.8063. Min Act: -0.0001

Data Index: 377103 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 2.5465. Min Range: -2.5465

Max Act: 1.8152. Min Act: -0.0000

Data Index: 110050 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 2.5465. Min Range: -2.5465

Max Act: 2.1256. Min Act: -0.0001

Data Index: 457237 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 2.5465. Min Range: -2.5465

Max Act: 1.9719. Min Act: -0.0001

Data Index: 1238698 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 2.5465. Min Range: -2.5465

Max Act: 1.9783. Min Act: -0.0000

Data Index: 923056 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 2.5465. Min Range: -2.5465

Max Act: 1.6359. Min Act: -0.0001

Data Index: 1217499 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 2.5465. Min Range: -2.5465

Max Act: 1.7756. Min Act: -0.0000

Data Index: 703404 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 2.5465. Min Range: -2.5465

Max Act: 1.7450. Min Act: -0.0000

Data Index: 84694 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 2.5465. Min Range: -2.5465

Max Act: 1.6523. Min Act: -0.0000

Data Index: 1327185 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 2.5465. Min Range: -2.5465

Max Act: 1.7856. Min Act: -0.0000

Data Index: 91224 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 2.5465. Min Range: -2.5465

Max Act: 1.7573. Min Act: -0.0001

Data Index: 1200141 (C4 (Web Text))

Max Activating Token Index: 749