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

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

Neuron 3086 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.8823. Min Act: -0.0000

Data Index: 787364 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.6616. Min Act: -0.0000

Data Index: 900403 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.7892. Min Act: -0.0000

Data Index: 1163772 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.5942. Min Act: -0.0000

Data Index: 538228 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.5526. Min Act: -0.0000

Data Index: 932535 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.5276. Min Act: -0.0000

Data Index: 883173 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.6646. Min Act: -0.0000

Data Index: 580821 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.5007. Min Act: -0.0000

Data Index: 690810 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.5113. Min Act: -0.0000

Data Index: 364910 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.6174. Min Act: -0.0000

Data Index: 218376 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.4664. Min Act: -0.0000

Data Index: 544402 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.3123. Min Act: -0.0000

Data Index: 1322946 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.4224. Min Act: -0.0000

Data Index: 293163 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.3988. Min Act: -0.0000

Data Index: 1356003 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.2742. Min Act: -0.0000

Data Index: 1294156 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.2637. Min Act: -0.0000

Data Index: 614036 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.3587. Min Act: -0.0000

Data Index: 897893 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.2022. Min Act: -0.0000

Data Index: 1290553 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.1513. Min Act: -0.0000

Data Index: 696745 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 2.8823. Min Range: -2.8823

Max Act: 2.2759. Min Act: -0.0000

Data Index: 244675 (C4 (Web Text))

Max Activating Token Index: 983