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

Dataset: The Pile

Neuron 1789 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1523076 (The Pile)

Max Activating Token Index: 990

Text #1

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1896013 (The Pile)

Max Activating Token Index: 236

Text #2

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1767947 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.7539. Min Act: -0.0000

Data Index: 441060 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1334360 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1785524 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1766773 (The Pile)

Max Activating Token Index: 901

Text #7

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1186805 (The Pile)

Max Activating Token Index: 341

Text #8

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.7054. Min Act: -0.0000

Data Index: 949028 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1900085 (The Pile)

Max Activating Token Index: 929

Text #10

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1512785 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6009. Min Act: -0.0000

Data Index: 806612 (The Pile)

Max Activating Token Index: 954

Text #12

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6156. Min Act: -0.0000

Data Index: 723669 (The Pile)

Max Activating Token Index: 381

Text #13

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1773659 (The Pile)

Max Activating Token Index: 205

Text #14

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6057. Min Act: -0.0000

Data Index: 286388 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5602. Min Act: -0.0000

Data Index: 249545 (The Pile)

Max Activating Token Index: 178

Text #16

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5518. Min Act: -0.0000

Data Index: 497133 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6201. Min Act: -0.0000

Data Index: 114620 (The Pile)

Max Activating Token Index: 695

Text #18

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1969987 (The Pile)

Max Activating Token Index: 635

Text #19

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1748089 (The Pile)

Max Activating Token Index: 270