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

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

Neuron 1994 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.6962. Min Act: -0.0000

Data Index: 333176 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5761. Min Act: -0.0001

Data Index: 1117817 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5658. Min Act: -0.0001

Data Index: 1010316 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5625. Min Act: -0.0000

Data Index: 843291 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5761. Min Act: -0.0000

Data Index: 772626 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5613. Min Act: -0.0000

Data Index: 712324 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1346679 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1090962 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5141. Min Act: -0.0001

Data Index: 1152633 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5114. Min Act: -0.0000

Data Index: 197852 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5092. Min Act: -0.0000

Data Index: 457571 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5248. Min Act: -0.0000

Data Index: 151756 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5202. Min Act: -0.0001

Data Index: 1345334 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4828. Min Act: -0.0001

Data Index: 1030571 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4876. Min Act: -0.0001

Data Index: 462251 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4809. Min Act: -0.0001

Data Index: 1119903 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4942. Min Act: -0.0000

Data Index: 185188 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4943. Min Act: -0.0000

Data Index: 691656 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1269189 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4739. Min Act: -0.0001

Data Index: 696518 (C4 (Web Text))

Max Activating Token Index: 534