Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 285 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.4549. Min Act: -0.0000

Data Index: 136691 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.3933. Min Act: -0.0000

Data Index: 943897 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.0765. Min Act: -0.0000

Data Index: 1038484 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.1727. Min Act: -0.0000

Data Index: 968061 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1217729 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.9494. Min Act: -0.0000

Data Index: 403202 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.2215. Min Act: -0.0000

Data Index: 616935 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.0281. Min Act: -0.0000

Data Index: 1013364 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.9351. Min Act: -0.0000

Data Index: 670065 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.8499. Min Act: -0.0000

Data Index: 542186 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1199604 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.9196. Min Act: -0.0000

Data Index: 759699 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.8593. Min Act: -0.0000

Data Index: 879564 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.9152. Min Act: -0.0000

Data Index: 351754 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.7847. Min Act: -0.0000

Data Index: 796521 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.9483. Min Act: -0.0000

Data Index: 454532 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.9699. Min Act: -0.0000

Data Index: 851412 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1276752 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.8743. Min Act: -0.0000

Data Index: 574159 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.9306. Min Act: -0.0000

Data Index: 521290 (C4 (Web Text))

Max Activating Token Index: 889