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

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

Neuron 3690 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2914. Min Act: 0.0000

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.3127. Min Act: -0.0000

Data Index: 514897 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1305019 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2999. Min Act: -0.0000

Data Index: 313082 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2802. Min Act: -0.0000

Data Index: 861685 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2788. Min Act: -0.0000

Data Index: 914876 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2639. Min Act: -0.0000

Data Index: 707691 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2846. Min Act: -0.0000

Data Index: 134436 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2595. Min Act: -0.0000

Data Index: 693661 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1187703 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1250245 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1105406 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1077763 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1215980 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2445. Min Act: 0.0000

Data Index: 1091122 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2501. Min Act: -0.0000

Data Index: 864345 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1015993 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2321. Min Act: -0.0000

Data Index: 736555 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1171544 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2351. Min Act: -0.0000

Data Index: 91004 (C4 (Web Text))

Max Activating Token Index: 688