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

Dataset: The Pile

Neuron 3174 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: 1.0134. Min Range: -1.0134

Max Act: 0.9219. Min Act: -0.0000

Data Index: 906874 (The Pile)

Max Activating Token Index: 385

Text #1

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.9792. Min Act: -0.0000

Data Index: 1664096 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.9702. Min Act: -0.0000

Data Index: 437046 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8716. Min Act: -0.0000

Data Index: 731067 (The Pile)

Max Activating Token Index: 702

Text #4

Max Range: 1.0134. Min Range: -1.0134

Max Act: 1.0134. Min Act: -0.0000

Data Index: 9781 (The Pile)

Max Activating Token Index: 852

Text #5

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1858696 (The Pile)

Max Activating Token Index: 479

Text #6

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.9058. Min Act: -0.0000

Data Index: 945296 (The Pile)

Max Activating Token Index: 541

Text #7

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1492567 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8212. Min Act: -0.0000

Data Index: 781432 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1971779 (The Pile)

Max Activating Token Index: 633

Text #10

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8798. Min Act: -0.0000

Data Index: 319080 (The Pile)

Max Activating Token Index: 915

Text #11

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8689. Min Act: -0.0000

Data Index: 497325 (The Pile)

Max Activating Token Index: 649

Text #12

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8670. Min Act: -0.0000

Data Index: 14487 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1229605 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7464. Min Act: -0.0000

Data Index: 421512 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1013855 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.9167. Min Act: -0.0000

Data Index: 124100 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1794503 (The Pile)

Max Activating Token Index: 238

Text #18

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8147. Min Act: -0.0000

Data Index: 1995479 (The Pile)

Max Activating Token Index: 789

Text #19

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1009531 (The Pile)

Max Activating Token Index: 699