Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 503 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.8246. Min Act: -0.0000

Data Index: 1272723 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.6067. Min Act: -0.0000

Data Index: 150105 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.5705. Min Act: -0.0001

Data Index: 1036038 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.5806. Min Act: -0.0001

Data Index: 1183393 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.2744. Min Act: -0.0000

Data Index: 690283 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.4007. Min Act: -0.0000

Data Index: 20055 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.1960. Min Act: -0.0000

Data Index: 786949 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.3219. Min Act: -0.0000

Data Index: 883086 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.0625. Min Act: -0.0000

Data Index: 143997 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.1857. Min Act: -0.0001

Data Index: 680585 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.1632. Min Act: -0.0001

Data Index: 288917 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.2998. Min Act: -0.0000

Data Index: 903277 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 4.8246. Min Range: -4.8246

Max Act: 3.9305. Min Act: -0.0000

Data Index: 129406 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 4.8246. Min Range: -4.8246

Max Act: 3.7525. Min Act: -0.0000

Data Index: 518827 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 4.8246. Min Range: -4.8246

Max Act: 3.9009. Min Act: -0.0001

Data Index: 178798 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.0200. Min Act: -0.0000

Data Index: 1003405 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 4.8246. Min Range: -4.8246

Max Act: 4.1053. Min Act: -0.0000

Data Index: 15468 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 4.8246. Min Range: -4.8246

Max Act: 3.7684. Min Act: -0.0001

Data Index: 508225 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 4.8246. Min Range: -4.8246

Max Act: 3.7503. Min Act: -0.0001

Data Index: 302112 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 4.8246. Min Range: -4.8246

Max Act: 3.6092. Min Act: -0.0000

Data Index: 437675 (C4 (Web Text))

Max Activating Token Index: 450