Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6062 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.6800. Min Act: -0.0000

Data Index: 995624 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.5577. Min Act: -0.0000

Data Index: 506755 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.5179. Min Act: -0.0000

Data Index: 731650 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.4580. Min Act: -0.0000

Data Index: 573534 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.6765. Min Act: -0.0000

Data Index: 1352698 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.2529. Min Act: -0.0000

Data Index: 265000 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.4677. Min Act: -0.0000

Data Index: 939131 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.3788. Min Act: -0.0000

Data Index: 910246 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.3244. Min Act: -0.0000

Data Index: 46028 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.2895. Min Act: -0.0000

Data Index: 1129301 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.2748. Min Act: -0.0000

Data Index: 935607 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.4122. Min Act: -0.0000

Data Index: 201057 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.4829. Min Act: -0.0000

Data Index: 42854 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.1142. Min Act: -0.0000

Data Index: 577704 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.1967. Min Act: -0.0000

Data Index: 725437 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.1992. Min Act: -0.0000

Data Index: 370612 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.2250. Min Act: -0.0000

Data Index: 119478 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.9450. Min Act: -0.0000

Data Index: 1052495 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.2770. Min Act: -0.0001

Data Index: 38537 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.1572. Min Act: -0.0000

Data Index: 810090 (C4 (Web Text))

Max Activating Token Index: 385