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

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

Neuron 1978 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0529. Min Range: -4.0529

Max Act: 4.0529. Min Act: -0.0000

Data Index: 25749 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.8735. Min Act: -0.0000

Data Index: 517272 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.7807. Min Act: -0.0000

Data Index: 973653 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.7817. Min Act: -0.0000

Data Index: 68379 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.6299. Min Act: -0.0000

Data Index: 245151 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.4031. Min Act: -0.0000

Data Index: 960518 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.5479. Min Act: -0.0000

Data Index: 266607 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.3265. Min Act: -0.0000

Data Index: 1099708 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.4544. Min Act: -0.0000

Data Index: 1145127 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.4438. Min Act: -0.0000

Data Index: 264232 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.4332. Min Act: -0.0000

Data Index: 941826 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.4290. Min Act: -0.0000

Data Index: 209624 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.2802. Min Act: -0.0000

Data Index: 722192 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.2631. Min Act: -0.0000

Data Index: 511037 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.3867. Min Act: -0.0000

Data Index: 1272635 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.3451. Min Act: -0.0000

Data Index: 902759 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.1759. Min Act: -0.0000

Data Index: 1213712 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.2888. Min Act: -0.0000

Data Index: 993497 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.1249. Min Act: -0.0000

Data Index: 810116 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 4.0529. Min Range: -4.0529

Max Act: 3.2778. Min Act: -0.0000

Data Index: 541331 (C4 (Web Text))

Max Activating Token Index: 995