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

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

Neuron 3701 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.8991. Min Act: -0.0000

Data Index: 698806 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.9248. Min Act: -0.0000

Data Index: 1056247 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.9077. Min Act: -0.0000

Data Index: 301527 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.8646. Min Act: -0.0000

Data Index: 66610 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.8808. Min Act: -0.0000

Data Index: 40088 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.9422. Min Act: -0.0000

Data Index: 818090 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.7314. Min Act: -0.0000

Data Index: 806611 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.9313. Min Act: -0.0000

Data Index: 572928 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.7337. Min Act: -0.0000

Data Index: 880299 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.9078. Min Act: -0.0000

Data Index: 926333 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.7229. Min Act: -0.0000

Data Index: 47155 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.7599. Min Act: -0.0000

Data Index: 534123 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.5349. Min Act: -0.0000

Data Index: 226582 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.7143. Min Act: -0.0000

Data Index: 816186 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 5.0758. Min Range: -5.0758

Max Act: 5.0758. Min Act: -0.0000

Data Index: 897600 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.7532. Min Act: -0.0000

Data Index: 420259 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.3865. Min Act: -0.0000

Data Index: 140956 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.2038. Min Act: -0.0000

Data Index: 352273 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.3518. Min Act: -0.0000

Data Index: 1111796 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 5.0758. Min Range: -5.0758

Max Act: 4.1030. Min Act: -0.0000

Data Index: 784120 (C4 (Web Text))

Max Activating Token Index: 21