Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3365 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.5056. Min Act: -0.0000

Data Index: 235646 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.4600. Min Act: -0.0000

Data Index: 553874 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.3701. Min Act: -0.0000

Data Index: 626214 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.3318. Min Act: -0.0000

Data Index: 734021 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.0576. Min Act: -0.0000

Data Index: 313350 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.0561. Min Act: -0.0000

Data Index: 1106962 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.0029. Min Act: -0.0000

Data Index: 1005677 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.0087. Min Act: -0.0000

Data Index: 24665 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.1681. Min Act: -0.0000

Data Index: 153690 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.1140. Min Act: -0.0000

Data Index: 497736 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.0878. Min Act: -0.0000

Data Index: 226589 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.2415. Min Act: -0.0000

Data Index: 1343197 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.0045. Min Act: -0.0000

Data Index: 292873 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.1695. Min Act: -0.0000

Data Index: 825263 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 4.5056. Min Range: -4.5056

Max Act: 3.9913. Min Act: -0.0000

Data Index: 195726 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.1753. Min Act: -0.0000

Data Index: 569933 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 4.5056. Min Range: -4.5056

Max Act: 3.9301. Min Act: -0.0000

Data Index: 314288 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 4.5056. Min Range: -4.5056

Max Act: 3.8942. Min Act: -0.0000

Data Index: 203120 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 4.5056. Min Range: -4.5056

Max Act: 3.8685. Min Act: -0.0000

Data Index: 746246 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.0192. Min Act: -0.0000

Data Index: 716721 (C4 (Web Text))

Max Activating Token Index: 635