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

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

Neuron 3098 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: 1.5668. Min Range: -1.5668

Max Act: 1.5668. Min Act: -0.0000

Data Index: 892803 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.3540. Min Act: -0.0000

Data Index: 402114 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.3843. Min Act: -0.0001

Data Index: 54581 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.4803. Min Act: -0.0001

Data Index: 836704 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.3505. Min Act: -0.0000

Data Index: 380019 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.2148. Min Act: -0.0001

Data Index: 135269 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.3261. Min Act: -0.0001

Data Index: 648701 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.1938. Min Act: -0.0000

Data Index: 524980 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.2583. Min Act: -0.0000

Data Index: 465388 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.2783. Min Act: -0.0001

Data Index: 1322691 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.2200. Min Act: -0.0001

Data Index: 752944 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.0300. Min Act: -0.0001

Data Index: 540125 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.1313. Min Act: -0.0000

Data Index: 759382 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.1903. Min Act: -0.0000

Data Index: 1228121 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.1966. Min Act: -0.0001

Data Index: 762506 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.0961. Min Act: -0.0000

Data Index: 316019 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.0409. Min Act: -0.0001

Data Index: 43697 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.0540. Min Act: -0.0001

Data Index: 746136 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.1007. Min Act: -0.0001

Data Index: 250911 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 1.5668. Min Range: -1.5668

Max Act: 1.0360. Min Act: -0.0001

Data Index: 645448 (C4 (Web Text))

Max Activating Token Index: 11