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

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

Neuron 5101 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: 2.9749. Min Range: -2.9749

Max Act: 2.9582. Min Act: -0.0000

Data Index: 167793 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.8193. Min Act: -0.0000

Data Index: 79928 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.9390. Min Act: -0.0000

Data Index: 553063 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.8093. Min Act: -0.0000

Data Index: 531820 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.7348. Min Act: -0.0000

Data Index: 887320 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.8658. Min Act: -0.0000

Data Index: 1336612 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.9749. Min Act: -0.0000

Data Index: 492493 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.8357. Min Act: -0.0000

Data Index: 1064812 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.6539. Min Act: -0.0000

Data Index: 965016 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.6408. Min Act: -0.0000

Data Index: 964972 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.8647. Min Act: -0.0000

Data Index: 157755 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.7660. Min Act: -0.0000

Data Index: 933501 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.7234. Min Act: -0.0000

Data Index: 777861 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.7297. Min Act: -0.0000

Data Index: 1029413 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.5754. Min Act: -0.0000

Data Index: 1258325 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.8140. Min Act: -0.0000

Data Index: 542970 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.6459. Min Act: -0.0000

Data Index: 688167 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.8419. Min Act: -0.0000

Data Index: 86646 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.6579. Min Act: -0.0000

Data Index: 1140097 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 2.9749. Min Range: -2.9749

Max Act: 2.6823. Min Act: -0.0000

Data Index: 535144 (C4 (Web Text))

Max Activating Token Index: 449