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

Dataset: The Pile

Neuron 290 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1361119 (The Pile)

Max Activating Token Index: 641

Text #1

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1912971 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.6038. Min Act: -0.0000

Data Index: 803778 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1000767 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5553. Min Act: -0.0000

Data Index: 816935 (The Pile)

Max Activating Token Index: 850

Text #5

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5471. Min Act: -0.0000

Data Index: 951921 (The Pile)

Max Activating Token Index: 309

Text #6

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1864723 (The Pile)

Max Activating Token Index: 946

Text #7

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1213147 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4065. Min Act: -0.0000

Data Index: 53924 (The Pile)

Max Activating Token Index: 130

Text #9

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1337430 (The Pile)

Max Activating Token Index: 251

Text #10

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4762. Min Act: -0.0000

Data Index: 120913 (The Pile)

Max Activating Token Index: 375

Text #11

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4388. Min Act: -0.0000

Data Index: 744536 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1277673 (The Pile)

Max Activating Token Index: 298

Text #13

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1694110 (The Pile)

Max Activating Token Index: 948

Text #14

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.3676. Min Act: -0.0000

Data Index: 665308 (The Pile)

Max Activating Token Index: 668

Text #15

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4180. Min Act: -0.0000

Data Index: 777194 (The Pile)

Max Activating Token Index: 453

Text #16

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4381. Min Act: -0.0000

Data Index: 125022 (The Pile)

Max Activating Token Index: 307

Text #17

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1232983 (The Pile)

Max Activating Token Index: 561

Text #18

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1269335 (The Pile)

Max Activating Token Index: 803

Text #19

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1176265 (The Pile)

Max Activating Token Index: 514