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

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

Neuron 2059 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.4788. Min Range: -5.4788

Max Act: 5.4383. Min Act: -0.0000

Data Index: 691049 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 5.4788. Min Range: -5.4788

Max Act: 4.8579. Min Act: -0.0000

Data Index: 580508 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 5.4788. Min Range: -5.4788

Max Act: 5.2505. Min Act: -0.0000

Data Index: 364366 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 5.4788. Min Range: -5.4788

Max Act: 5.4788. Min Act: -0.0000

Data Index: 520650 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 5.4788. Min Range: -5.4788

Max Act: 5.2809. Min Act: -0.0000

Data Index: 733560 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 5.4788. Min Range: -5.4788

Max Act: 5.2804. Min Act: -0.0000

Data Index: 995044 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 5.4788. Min Range: -5.4788

Max Act: 4.7737. Min Act: -0.0000

Data Index: 353659 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 5.4788. Min Range: -5.4788

Max Act: 5.0919. Min Act: -0.0000

Data Index: 375847 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 5.4788. Min Range: -5.4788

Max Act: 5.0200. Min Act: -0.0000

Data Index: 595941 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 5.4788. Min Range: -5.4788

Max Act: 4.9235. Min Act: -0.0000

Data Index: 1311638 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 5.4788. Min Range: -5.4788

Max Act: 5.1083. Min Act: -0.0000

Data Index: 320008 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 5.4788. Min Range: -5.4788

Max Act: 4.8843. Min Act: -0.0000

Data Index: 365309 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 5.4788. Min Range: -5.4788

Max Act: 4.6234. Min Act: -0.0000

Data Index: 647589 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 5.4788. Min Range: -5.4788

Max Act: 4.7391. Min Act: -0.0000

Data Index: 748811 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 5.4788. Min Range: -5.4788

Max Act: 4.8762. Min Act: -0.0000

Data Index: 803018 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 5.4788. Min Range: -5.4788

Max Act: 4.2776. Min Act: -0.0000

Data Index: 1002964 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 5.4788. Min Range: -5.4788

Max Act: 4.2446. Min Act: -0.0000

Data Index: 908625 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 5.4788. Min Range: -5.4788

Max Act: 4.4381. Min Act: -0.0000

Data Index: 201571 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 5.4788. Min Range: -5.4788

Max Act: 4.3904. Min Act: -0.0000

Data Index: 390031 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 5.4788. Min Range: -5.4788

Max Act: 4.1118. Min Act: -0.0000

Data Index: 1027877 (C4 (Web Text))

Max Activating Token Index: 749