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

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

Neuron 2112 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.8725. Min Act: -0.0001

Data Index: 479454 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.8760. Min Act: -0.0001

Data Index: 223439 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.8002. Min Act: -0.0001

Data Index: 1310226 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.8465. Min Act: -0.0001

Data Index: 654846 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.8205. Min Act: -0.0001

Data Index: 1120592 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7894. Min Act: -0.0001

Data Index: 329750 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.8163. Min Act: -0.0001

Data Index: 1121438 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.8257. Min Act: -0.0001

Data Index: 163607 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.8242. Min Act: -0.0001

Data Index: 38477 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7976. Min Act: -0.0001

Data Index: 1124492 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7860. Min Act: -0.0001

Data Index: 179125 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7829. Min Act: -0.0001

Data Index: 875133 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7272. Min Act: -0.0001

Data Index: 442009 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7696. Min Act: -0.0001

Data Index: 272048 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7576. Min Act: -0.0001

Data Index: 227042 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7265. Min Act: -0.0001

Data Index: 1090576 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7079. Min Act: -0.0001

Data Index: 884871 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7362. Min Act: -0.0001

Data Index: 678084 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7530. Min Act: -0.0001

Data Index: 1257851 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7473. Min Act: -0.0001

Data Index: 7868 (C4 (Web Text))

Max Activating Token Index: 848