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

Dataset: The Pile

Neuron 3701 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.7374. Min Act: -0.0000

Data Index: 502456 (The Pile)

Max Activating Token Index: 740

Text #1

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.6232. Min Act: -0.0000

Data Index: 1414029 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.3648. Min Act: -0.0000

Data Index: 1242536 (The Pile)

Max Activating Token Index: 878

Text #3

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.3850. Min Act: -0.0000

Data Index: 616719 (The Pile)

Max Activating Token Index: 899

Text #4

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.4135. Min Act: -0.0000

Data Index: 1927126 (The Pile)

Max Activating Token Index: 607

Text #5

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.4560. Min Act: -0.0000

Data Index: 1688828 (The Pile)

Max Activating Token Index: 741

Text #6

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.3103. Min Act: -0.0000

Data Index: 1663718 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.3977. Min Act: -0.0000

Data Index: 1435642 (The Pile)

Max Activating Token Index: 113

Text #8

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.3703. Min Act: -0.0000

Data Index: 300650 (The Pile)

Max Activating Token Index: 265

Text #9

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.3204. Min Act: -0.0000

Data Index: 1068887 (The Pile)

Max Activating Token Index: 220

Text #10

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.3129. Min Act: -0.0000

Data Index: 472196 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.2847. Min Act: -0.0000

Data Index: 908109 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.2553. Min Act: -0.0000

Data Index: 1785086 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.2611. Min Act: -0.0000

Data Index: 683552 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.2616. Min Act: -0.0000

Data Index: 1348350 (The Pile)

Max Activating Token Index: 720

Text #15

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.3304. Min Act: -0.0000

Data Index: 496678 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.2550. Min Act: -0.0000

Data Index: 1241866 (The Pile)

Max Activating Token Index: 232

Text #17

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.2556. Min Act: -0.0000

Data Index: 936878 (The Pile)

Max Activating Token Index: 579

Text #18

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.2430. Min Act: -0.0000

Data Index: 1230339 (The Pile)

Max Activating Token Index: 321

Text #19

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.2380. Min Act: -0.0000

Data Index: 1141985 (The Pile)

Max Activating Token Index: 882