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

Dataset: The Pile

Neuron 4095 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: 0.9610. Min Range: -0.9610

Max Act: 0.9610. Min Act: -0.0000

Data Index: 16790 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1577278 (The Pile)

Max Activating Token Index: 126

Text #2

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1550301 (The Pile)

Max Activating Token Index: 156

Text #3

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1296873 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1119340 (The Pile)

Max Activating Token Index: 84

Text #5

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1206258 (The Pile)

Max Activating Token Index: 698

Text #6

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6830. Min Act: -0.0000

Data Index: 779415 (The Pile)

Max Activating Token Index: 894

Text #7

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1410191 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1878198 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1456052 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1073256 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7192. Min Act: -0.0000

Data Index: 20148 (The Pile)

Max Activating Token Index: 787

Text #12

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1698522 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1287240 (The Pile)

Max Activating Token Index: 877

Text #14

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1876523 (The Pile)

Max Activating Token Index: 4

Text #15

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6729. Min Act: -0.0000

Data Index: 808575 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6520. Min Act: -0.0000

Data Index: 72962 (The Pile)

Max Activating Token Index: 334

Text #17

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1130428 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1506328 (The Pile)

Max Activating Token Index: 931

Text #19

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6656. Min Act: -0.0000

Data Index: 718002 (The Pile)

Max Activating Token Index: 11