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

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

Neuron 897 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: 0.6109. Min Range: -0.6109

Max Act: 0.6109. Min Act: -0.0000

Data Index: 693404 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.4954. Min Act: -0.0000

Data Index: 481656 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.4513. Min Act: -0.0000

Data Index: 798355 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.4250. Min Act: -0.0000

Data Index: 435367 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1315685 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3845. Min Act: -0.0000

Data Index: 858775 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.4150. Min Act: -0.0000

Data Index: 922471 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3546. Min Act: -0.0000

Data Index: 574581 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3562. Min Act: -0.0000

Data Index: 1639220 (Python Code)

Max Activating Token Index: 96

Text #9

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3089. Min Act: -0.0000

Data Index: 562051 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1523086 (Python Code)

Max Activating Token Index: 475

Text #11

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3447. Min Act: -0.0000

Data Index: 120486 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3233. Min Act: -0.0000

Data Index: 948535 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1473230 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1486464 (Python Code)

Max Activating Token Index: 636

Text #15

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3176. Min Act: -0.0000

Data Index: 822419 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3289. Min Act: -0.0000

Data Index: 1576279 (Python Code)

Max Activating Token Index: 714

Text #17

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3157. Min Act: -0.0000

Data Index: 973509 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3135. Min Act: -0.0000

Data Index: 620870 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.6109. Min Range: -0.6109

Max Act: 0.3077. Min Act: -0.0000

Data Index: 516313 (C4 (Web Text))

Max Activating Token Index: 799