Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1245 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7499. Min Act: -0.0003

Data Index: 1039940 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7964. Min Act: -0.0003

Data Index: 611370 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7546. Min Act: -0.0003

Data Index: 769992 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7279. Min Act: -0.0003

Data Index: 28567 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7608. Min Act: -0.0003

Data Index: 1232427 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7312. Min Act: -0.0003

Data Index: 1023838 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7534. Min Act: -0.0003

Data Index: 591328 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7485. Min Act: -0.0003

Data Index: 968759 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7403. Min Act: -0.0003

Data Index: 139046 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.6886. Min Act: -0.0003

Data Index: 784185 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7316. Min Act: -0.0003

Data Index: 107791 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7701. Min Act: -0.0003

Data Index: 779417 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7741. Min Act: -0.0003

Data Index: 151350 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.6787. Min Act: -0.0003

Data Index: 969817 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7098. Min Act: -0.0003

Data Index: 805966 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7915. Min Act: -0.0003

Data Index: 557465 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.6474. Min Act: -0.0003

Data Index: 562999 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.6913. Min Act: -0.0003

Data Index: 603590 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7889. Min Act: -0.0003

Data Index: 893211 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5978. Min Act: -0.0003

Data Index: 1298320 (C4 (Web Text))

Max Activating Token Index: 641