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

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

Neuron 3607 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1210639 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.3530. Min Act: -0.0000

Data Index: 14827 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.3200. Min Act: -0.0000

Data Index: 643488 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2844. Min Act: -0.0000

Data Index: 263026 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2320. Min Act: -0.0000

Data Index: 836569 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2122. Min Act: -0.0000

Data Index: 747524 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2210. Min Act: -0.0001

Data Index: 862953 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2175. Min Act: -0.0001

Data Index: 353927 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2168. Min Act: 0.0000

Data Index: 454311 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2125. Min Act: -0.0000

Data Index: 899871 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2020. Min Act: -0.0000

Data Index: 710311 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.1951. Min Act: -0.0001

Data Index: 547412 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2129. Min Act: -0.0000

Data Index: 697805 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.1997. Min Act: -0.0001

Data Index: 895969 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2046. Min Act: -0.0001

Data Index: 626876 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2081. Min Act: -0.0001

Data Index: 509860 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.1986. Min Act: -0.0001

Data Index: 1221045 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.1966. Min Act: -0.0000

Data Index: 774517 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.1953. Min Act: -0.0001

Data Index: 525299 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.1877. Min Act: -0.0001

Data Index: 854154 (C4 (Web Text))

Max Activating Token Index: 382