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

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

Neuron 4863 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7979. Min Range: -5.7979

Max Act: 5.7460. Min Act: -0.0000

Data Index: 1010931 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 5.7979. Min Range: -5.7979

Max Act: 5.7979. Min Act: -0.0000

Data Index: 613262 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 5.7979. Min Range: -5.7979

Max Act: 5.4623. Min Act: -0.0000

Data Index: 484315 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 5.7979. Min Range: -5.7979

Max Act: 5.4707. Min Act: -0.0000

Data Index: 255989 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 5.7979. Min Range: -5.7979

Max Act: 4.9027. Min Act: -0.0000

Data Index: 550550 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 5.7979. Min Range: -5.7979

Max Act: 4.5910. Min Act: -0.0000

Data Index: 469289 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 5.7979. Min Range: -5.7979

Max Act: 4.5273. Min Act: -0.0000

Data Index: 289705 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 5.7979. Min Range: -5.7979

Max Act: 5.2341. Min Act: -0.0000

Data Index: 315754 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 5.7979. Min Range: -5.7979

Max Act: 4.5783. Min Act: -0.0000

Data Index: 323416 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 5.7979. Min Range: -5.7979

Max Act: 5.0880. Min Act: -0.0000

Data Index: 509228 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 5.7979. Min Range: -5.7979

Max Act: 4.7082. Min Act: -0.0000

Data Index: 1327012 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 5.7979. Min Range: -5.7979

Max Act: 4.8446. Min Act: -0.0000

Data Index: 526827 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 5.7979. Min Range: -5.7979

Max Act: 4.6640. Min Act: -0.0000

Data Index: 742312 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 5.7979. Min Range: -5.7979

Max Act: 4.4760. Min Act: -0.0001

Data Index: 1080416 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 5.7979. Min Range: -5.7979

Max Act: 4.0199. Min Act: -0.0000

Data Index: 516059 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 5.7979. Min Range: -5.7979

Max Act: 4.5131. Min Act: -0.0000

Data Index: 928576 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 5.7979. Min Range: -5.7979

Max Act: 4.2955. Min Act: -0.0000

Data Index: 412459 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 5.7979. Min Range: -5.7979

Max Act: 4.0960. Min Act: -0.0000

Data Index: 1079797 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 5.7979. Min Range: -5.7979

Max Act: 3.9944. Min Act: -0.0000

Data Index: 794139 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 5.7979. Min Range: -5.7979

Max Act: 3.9805. Min Act: -0.0000

Data Index: 1279357 (C4 (Web Text))

Max Activating Token Index: 115