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

Dataset: The Pile

Neuron 1706 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.6952. Min Act: -0.0000

Data Index: 297009 (The Pile)

Max Activating Token Index: 508

Text #1

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1107889 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1926875 (The Pile)

Max Activating Token Index: 319

Text #3

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.6232. Min Act: -0.0000

Data Index: 261200 (The Pile)

Max Activating Token Index: 375

Text #4

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5783. Min Act: -0.0000

Data Index: 105122 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5872. Min Act: -0.0000

Data Index: 672548 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5505. Min Act: -0.0000

Data Index: 603089 (The Pile)

Max Activating Token Index: 532

Text #7

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1572362 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5435. Min Act: -0.0000

Data Index: 886615 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5009. Min Act: -0.0000

Data Index: 995994 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1573975 (The Pile)

Max Activating Token Index: 771

Text #11

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1306100 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1800429 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1586211 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4492. Min Act: -0.0000

Data Index: 133012 (The Pile)

Max Activating Token Index: 240

Text #15

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4446. Min Act: -0.0000

Data Index: 44126 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1327888 (The Pile)

Max Activating Token Index: 235

Text #17

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1692401 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4067. Min Act: -0.0000

Data Index: 458068 (The Pile)

Max Activating Token Index: 638

Text #19

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4776. Min Act: -0.0000

Data Index: 878846 (The Pile)

Max Activating Token Index: 96