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

Dataset: The Pile

Neuron 2830 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: 0.6386. Min Range: -0.6386

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1343056 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5669. Min Act: -0.0000

Data Index: 745144 (The Pile)

Max Activating Token Index: 890

Text #2

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6364. Min Act: -0.0000

Data Index: 368292 (The Pile)

Max Activating Token Index: 797

Text #3

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5794. Min Act: -0.0000

Data Index: 317885 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1752162 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5383. Min Act: -0.0000

Data Index: 338448 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1001106 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5082. Min Act: -0.0000

Data Index: 1873119 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5081. Min Act: -0.0000

Data Index: 1030653 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1187551 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1027478 (The Pile)

Max Activating Token Index: 139

Text #11

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4595. Min Act: -0.0000

Data Index: 128941 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1197877 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4789. Min Act: -0.0000

Data Index: 979538 (The Pile)

Max Activating Token Index: 911

Text #14

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1800110 (The Pile)

Max Activating Token Index: 703

Text #15

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1513876 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1232795 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1744899 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4438. Min Act: -0.0000

Data Index: 681287 (The Pile)

Max Activating Token Index: 6

Text #19

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4506. Min Act: -0.0000

Data Index: 148529 (The Pile)

Max Activating Token Index: 132