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

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

Neuron 4876 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: 1.3024. Min Range: -1.3024

Max Act: 1.3024. Min Act: -0.0000

Data Index: 241209 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 1.3024. Min Range: -1.3024

Max Act: 1.2676. Min Act: -0.0000

Data Index: 435209 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 1.3024. Min Range: -1.3024

Max Act: 1.0143. Min Act: -0.0000

Data Index: 415913 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.9593. Min Act: -0.0000

Data Index: 616136 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.9653. Min Act: -0.0000

Data Index: 886917 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.8761. Min Act: -0.0000

Data Index: 405456 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.8373. Min Act: -0.0000

Data Index: 581912 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.8261. Min Act: -0.0000

Data Index: 820801 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.8516. Min Act: -0.0000

Data Index: 983646 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1340369 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.6597. Min Act: -0.0000

Data Index: 123867 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.5960. Min Act: -0.0000

Data Index: 502055 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.5358. Min Act: -0.0000

Data Index: 891373 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.5585. Min Act: -0.0000

Data Index: 657165 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1165185 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1038455 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.5398. Min Act: -0.0000

Data Index: 712274 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.4921. Min Act: -0.0000

Data Index: 759570 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1025158 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.4157. Min Act: -0.0000

Data Index: 229460 (C4 (Web Text))

Max Activating Token Index: 792