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

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

Neuron 1724 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7788. Min Range: -6.7788

Max Act: 6.7788. Min Act: -0.0000

Data Index: 620912 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 6.7788. Min Range: -6.7788

Max Act: 6.2512. Min Act: -0.0000

Data Index: 701755 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 6.7788. Min Range: -6.7788

Max Act: 6.3233. Min Act: -0.0000

Data Index: 384410 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 6.7788. Min Range: -6.7788

Max Act: 6.3030. Min Act: -0.0000

Data Index: 923603 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 6.7788. Min Range: -6.7788

Max Act: 5.7454. Min Act: -0.0000

Data Index: 787732 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 6.7788. Min Range: -6.7788

Max Act: 5.4700. Min Act: -0.0000

Data Index: 143546 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 6.7788. Min Range: -6.7788

Max Act: 5.0159. Min Act: -0.0000

Data Index: 142020 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 6.7788. Min Range: -6.7788

Max Act: 5.1996. Min Act: -0.0000

Data Index: 1089799 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 6.7788. Min Range: -6.7788

Max Act: 4.8387. Min Act: -0.0001

Data Index: 237863 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 6.7788. Min Range: -6.7788

Max Act: 5.2425. Min Act: -0.0000

Data Index: 794446 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 6.7788. Min Range: -6.7788

Max Act: 5.0513. Min Act: -0.0000

Data Index: 1313893 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 6.7788. Min Range: -6.7788

Max Act: 5.3485. Min Act: -0.0000

Data Index: 563810 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 6.7788. Min Range: -6.7788

Max Act: 5.0463. Min Act: -0.0001

Data Index: 1347486 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 6.7788. Min Range: -6.7788

Max Act: 5.0408. Min Act: -0.0000

Data Index: 202056 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 6.7788. Min Range: -6.7788

Max Act: 4.8917. Min Act: -0.0000

Data Index: 506190 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 6.7788. Min Range: -6.7788

Max Act: 4.9437. Min Act: -0.0000

Data Index: 45060 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 6.7788. Min Range: -6.7788

Max Act: 4.4663. Min Act: -0.0001

Data Index: 268121 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 6.7788. Min Range: -6.7788

Max Act: 4.9463. Min Act: -0.0000

Data Index: 30366 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 6.7788. Min Range: -6.7788

Max Act: 4.7100. Min Act: -0.0000

Data Index: 713321 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 6.7788. Min Range: -6.7788

Max Act: 4.6904. Min Act: -0.0000

Data Index: 649590 (C4 (Web Text))

Max Activating Token Index: 228