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

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

Neuron 2840 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.1721. Min Act: -0.0000

Data Index: 812597 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.1966. Min Act: -0.0001

Data Index: 1153474 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0603. Min Act: -0.0000

Data Index: 751158 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.1152. Min Act: -0.0001

Data Index: 829854 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0789. Min Act: -0.0001

Data Index: 90223 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0668. Min Act: -0.0001

Data Index: 278379 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0132. Min Act: -0.0001

Data Index: 470852 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.1128. Min Act: -0.0000

Data Index: 1211864 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0159. Min Act: -0.0001

Data Index: 125031 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0369. Min Act: -0.0001

Data Index: 1144083 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0018. Min Act: -0.0000

Data Index: 632703 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9609. Min Act: -0.0001

Data Index: 315033 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0163. Min Act: -0.0000

Data Index: 728310 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0020. Min Act: -0.0001

Data Index: 738155 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9964. Min Act: -0.0000

Data Index: 643145 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9936. Min Act: -0.0000

Data Index: 191563 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9814. Min Act: -0.0001

Data Index: 599097 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9801. Min Act: -0.0001

Data Index: 493498 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0105. Min Act: -0.0001

Data Index: 244360 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0050. Min Act: -0.0001

Data Index: 630942 (C4 (Web Text))

Max Activating Token Index: 538