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

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

Neuron 1279 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.0009. Min Act: -0.0001

Data Index: 847222 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.1248. Min Act: -0.0001

Data Index: 920814 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 3.1870. Min Range: -3.1870

Max Act: 3.1870. Min Act: -0.0001

Data Index: 539802 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.7691. Min Act: -0.0001

Data Index: 973168 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.9866. Min Act: -0.0001

Data Index: 720631 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.7608. Min Act: -0.0001

Data Index: 71774 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.6156. Min Act: -0.0001

Data Index: 145595 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.5903. Min Act: -0.0001

Data Index: 1342638 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.6619. Min Act: -0.0001

Data Index: 463907 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.4844. Min Act: -0.0001

Data Index: 770547 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.6001. Min Act: -0.0001

Data Index: 880975 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.5710. Min Act: -0.0001

Data Index: 1225977 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.6844. Min Act: -0.0001

Data Index: 1005746 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.6585. Min Act: -0.0001

Data Index: 384086 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.5301. Min Act: -0.0001

Data Index: 1310197 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.6534. Min Act: -0.0001

Data Index: 748722 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.4051. Min Act: -0.0001

Data Index: 123432 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.5005. Min Act: -0.0001

Data Index: 711749 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.6141. Min Act: -0.0001

Data Index: 77457 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 3.1870. Min Range: -3.1870

Max Act: 2.6036. Min Act: -0.0001

Data Index: 559921 (C4 (Web Text))

Max Activating Token Index: 698