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

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

Neuron 3042 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.8647. Min Act: -0.0000

Data Index: 831300 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.6739. Min Act: -0.0000

Data Index: 952652 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.5190. Min Act: -0.0000

Data Index: 1290675 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1323448 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.3190. Min Act: -0.0000

Data Index: 104518 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.3203. Min Act: -0.0000

Data Index: 121340 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.3125. Min Act: -0.0000

Data Index: 245666 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.3522. Min Act: -0.0000

Data Index: 176475 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.4923. Min Act: -0.0000

Data Index: 888297 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.2848. Min Act: -0.0000

Data Index: 901783 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.2914. Min Act: -0.0000

Data Index: 543440 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.1743. Min Act: -0.0000

Data Index: 991762 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.2168. Min Act: -0.0000

Data Index: 440219 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.2566. Min Act: -0.0000

Data Index: 917491 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.1563. Min Act: -0.0000

Data Index: 534850 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.1300. Min Act: -0.0000

Data Index: 1199529 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.1453. Min Act: -0.0000

Data Index: 978085 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.1394. Min Act: -0.0000

Data Index: 862375 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.1148. Min Act: -0.0000

Data Index: 30380 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 1.8647. Min Range: -1.8647

Max Act: 1.0593. Min Act: -0.0000

Data Index: 1027653 (C4 (Web Text))

Max Activating Token Index: 154