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

Dataset: The Pile

Neuron 1594 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.9093. Min Act: -0.0000

Data Index: 230065 (The Pile)

Max Activating Token Index: 894

Text #1

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1610542 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1865022 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1321714 (The Pile)

Max Activating Token Index: 409

Text #4

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.8240. Min Act: -0.0000

Data Index: 657204 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.8527. Min Act: -0.0000

Data Index: 494442 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1311183 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.8159. Min Act: -0.0000

Data Index: 303289 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1082753 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1615372 (The Pile)

Max Activating Token Index: 291

Text #10

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.8020. Min Act: -0.0000

Data Index: 330050 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1250768 (The Pile)

Max Activating Token Index: 228

Text #12

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1718780 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1993076 (The Pile)

Max Activating Token Index: 17

Text #14

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7583. Min Act: -0.0000

Data Index: 552119 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7712. Min Act: -0.0000

Data Index: 833223 (The Pile)

Max Activating Token Index: 792

Text #16

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1944354 (The Pile)

Max Activating Token Index: 465

Text #17

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1997783 (The Pile)

Max Activating Token Index: 457

Text #18

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7697. Min Act: -0.0000

Data Index: 701356 (The Pile)

Max Activating Token Index: 256

Text #19

Max Range: 0.9093. Min Range: -0.9093

Max Act: 0.7184. Min Act: -0.0000

Data Index: 117168 (The Pile)

Max Activating Token Index: 747