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

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

Neuron 654 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: 3.5169. Min Range: -3.5169

Max Act: 3.4302. Min Act: -0.0001

Data Index: 24816 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.2645. Min Act: -0.0001

Data Index: 56916 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.3964. Min Act: -0.0001

Data Index: 184643 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.2132. Min Act: -0.0001

Data Index: 998224 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.5169. Min Act: -0.0001

Data Index: 1288828 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.1099. Min Act: -0.0001

Data Index: 664698 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.1242. Min Act: -0.0001

Data Index: 1298599 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.2613. Min Act: -0.0001

Data Index: 1140969 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.2417. Min Act: -0.0001

Data Index: 427886 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 3.5169. Min Range: -3.5169

Max Act: 2.9273. Min Act: -0.0001

Data Index: 190136 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.0793. Min Act: -0.0001

Data Index: 1304247 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.0474. Min Act: -0.0001

Data Index: 1195632 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.1562. Min Act: -0.0001

Data Index: 821018 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.2680. Min Act: -0.0001

Data Index: 1145939 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 3.5169. Min Range: -3.5169

Max Act: 2.9927. Min Act: -0.0001

Data Index: 916029 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 3.5169. Min Range: -3.5169

Max Act: 3.2434. Min Act: -0.0001

Data Index: 1063169 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 3.5169. Min Range: -3.5169

Max Act: 2.9458. Min Act: -0.0001

Data Index: 450564 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 3.5169. Min Range: -3.5169

Max Act: 2.7060. Min Act: -0.0001

Data Index: 1065330 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 3.5169. Min Range: -3.5169

Max Act: 2.9532. Min Act: -0.0001

Data Index: 667210 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 3.5169. Min Range: -3.5169

Max Act: 2.6226. Min Act: -0.0001

Data Index: 156696 (C4 (Web Text))

Max Activating Token Index: 274