Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3703 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.2914. Min Act: -0.0001

Data Index: 1322378 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.2828. Min Act: -0.0001

Data Index: 314884 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.2350. Min Act: -0.0001

Data Index: 374131 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.1882. Min Act: -0.0000

Data Index: 737418 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.2066. Min Act: -0.0001

Data Index: 1067257 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.1729. Min Act: -0.0001

Data Index: 1099264 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.1320. Min Act: -0.0001

Data Index: 55486 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.0592. Min Act: -0.0001

Data Index: 957902 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.1563. Min Act: -0.0001

Data Index: 540696 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.0877. Min Act: -0.0001

Data Index: 470796 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.0690. Min Act: -0.0001

Data Index: 81691 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.0523. Min Act: -0.0001

Data Index: 1281427 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.0876. Min Act: -0.0001

Data Index: 1091838 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.0137. Min Act: -0.0001

Data Index: 443094 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.0125. Min Act: -0.0001

Data Index: 1098873 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 1.2914. Min Range: -1.2914

Max Act: 0.9785. Min Act: -0.0001

Data Index: 900990 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.0260. Min Act: -0.0001

Data Index: 434066 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 1.2914. Min Range: -1.2914

Max Act: 0.9798. Min Act: -0.0001

Data Index: 949525 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.0101. Min Act: -0.0000

Data Index: 764858 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 1.2914. Min Range: -1.2914

Max Act: 1.0046. Min Act: -0.0001

Data Index: 1319456 (C4 (Web Text))

Max Activating Token Index: 890