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

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

Neuron 2909 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: 2.6743. Min Range: -2.6743

Max Act: 2.6743. Min Act: -0.0000

Data Index: 829334 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.5391. Min Act: -0.0000

Data Index: 1024383 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.5545. Min Act: -0.0000

Data Index: 1077470 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.5561. Min Act: -0.0000

Data Index: 1062163 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.5139. Min Act: -0.0000

Data Index: 1276114 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.4730. Min Act: -0.0000

Data Index: 386395 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.4553. Min Act: -0.0001

Data Index: 614707 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.4966. Min Act: -0.0000

Data Index: 695020 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.3655. Min Act: -0.0001

Data Index: 1190576 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.4240. Min Act: -0.0000

Data Index: 241817 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.3461. Min Act: -0.0000

Data Index: 597972 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.3323. Min Act: -0.0000

Data Index: 827180 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.3589. Min Act: -0.0000

Data Index: 1207431 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.3239. Min Act: -0.0000

Data Index: 684781 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.1561. Min Act: -0.0001

Data Index: 993494 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.2937. Min Act: -0.0000

Data Index: 50105 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.2197. Min Act: -0.0001

Data Index: 879197 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.2754. Min Act: -0.0001

Data Index: 1580543 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.1331. Min Act: -0.0000

Data Index: 1349838 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 2.6743. Min Range: -2.6743

Max Act: 2.1854. Min Act: -0.0000

Data Index: 403471 (C4 (Web Text))

Max Activating Token Index: 915