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

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

Neuron 2702 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7925. Min Range: -5.7925

Max Act: 5.7925. Min Act: -0.0000

Data Index: 473091 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 5.7925. Min Range: -5.7925

Max Act: 5.3548. Min Act: -0.0000

Data Index: 901904 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 5.7925. Min Range: -5.7925

Max Act: 5.3309. Min Act: -0.0000

Data Index: 1032564 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 5.7925. Min Range: -5.7925

Max Act: 5.1935. Min Act: -0.0000

Data Index: 917198 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 5.7925. Min Range: -5.7925

Max Act: 5.0848. Min Act: -0.0000

Data Index: 963701 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 5.7925. Min Range: -5.7925

Max Act: 5.0300. Min Act: -0.0000

Data Index: 655145 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.7943. Min Act: -0.0000

Data Index: 120103 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.8068. Min Act: -0.0000

Data Index: 456145 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.7656. Min Act: -0.0000

Data Index: 457163 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.8566. Min Act: -0.0000

Data Index: 640179 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.8405. Min Act: -0.0000

Data Index: 95228 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.9427. Min Act: -0.0000

Data Index: 198120 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.7492. Min Act: -0.0000

Data Index: 684018 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.5102. Min Act: -0.0000

Data Index: 288457 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.7103. Min Act: -0.0000

Data Index: 909010 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.4599. Min Act: -0.0000

Data Index: 939453 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.4144. Min Act: -0.0000

Data Index: 31710 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.5026. Min Act: -0.0000

Data Index: 700057 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.3080. Min Act: -0.0000

Data Index: 928817 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 5.7925. Min Range: -5.7925

Max Act: 4.5111. Min Act: -0.0000

Data Index: 664235 (C4 (Web Text))

Max Activating Token Index: 539