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

Dataset: The Pile

Neuron 1573 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: 0.8703. Min Range: -0.8703

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1799336 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.8422. Min Act: -0.0000

Data Index: 901607 (The Pile)

Max Activating Token Index: 557

Text #2

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.8703. Min Act: -0.0000

Data Index: 1916739 (The Pile)

Max Activating Token Index: 445

Text #3

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1005061 (The Pile)

Max Activating Token Index: 909

Text #4

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7615. Min Act: -0.0000

Data Index: 643739 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1464765 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7037. Min Act: -0.0000

Data Index: 797146 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6997. Min Act: -0.0000

Data Index: 203605 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1650142 (The Pile)

Max Activating Token Index: 119

Text #9

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1747789 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.5961. Min Act: -0.0000

Data Index: 826086 (The Pile)

Max Activating Token Index: 216

Text #11

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1475788 (The Pile)

Max Activating Token Index: 725

Text #12

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6319. Min Act: -0.0000

Data Index: 581092 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6280. Min Act: -0.0000

Data Index: 30230 (The Pile)

Max Activating Token Index: 245

Text #14

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6261. Min Act: -0.0000

Data Index: 768077 (The Pile)

Max Activating Token Index: 121

Text #15

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6172. Min Act: -0.0000

Data Index: 419027 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1096176 (The Pile)

Max Activating Token Index: 808

Text #17

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6050. Min Act: -0.0000

Data Index: 662222 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1818905 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1853075 (The Pile)

Max Activating Token Index: 243