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

Dataset: The Pile

Neuron 3424 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: 1.7483. Min Range: -1.7483

Max Act: 1.7002. Min Act: -0.0000

Data Index: 555623 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.7428. Min Act: -0.0000

Data Index: 975400 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.7483. Min Act: -0.0000

Data Index: 1480602 (The Pile)

Max Activating Token Index: 11

Text #3

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.6533. Min Act: -0.0000

Data Index: 263888 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.5873. Min Act: -0.0000

Data Index: 434666 (The Pile)

Max Activating Token Index: 95

Text #5

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.5175. Min Act: -0.0000

Data Index: 1873489 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.5470. Min Act: -0.0000

Data Index: 1639829 (The Pile)

Max Activating Token Index: 569

Text #7

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.6415. Min Act: -0.0000

Data Index: 808926 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.5376. Min Act: -0.0000

Data Index: 1306265 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.4602. Min Act: -0.0000

Data Index: 1231458 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.5477. Min Act: -0.0000

Data Index: 1044111 (The Pile)

Max Activating Token Index: 716

Text #11

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.5195. Min Act: -0.0000

Data Index: 1593216 (The Pile)

Max Activating Token Index: 741

Text #12

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.4606. Min Act: -0.0000

Data Index: 586662 (The Pile)

Max Activating Token Index: 802

Text #13

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.3511. Min Act: -0.0000

Data Index: 994781 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1083268 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.4107. Min Act: -0.0000

Data Index: 1796234 (The Pile)

Max Activating Token Index: 266

Text #16

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.4557. Min Act: -0.0000

Data Index: 1232095 (The Pile)

Max Activating Token Index: 306

Text #17

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.3100. Min Act: -0.0000

Data Index: 1426257 (The Pile)

Max Activating Token Index: 218

Text #18

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.3316. Min Act: -0.0000

Data Index: 1395073 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 1.7483. Min Range: -1.7483

Max Act: 1.2890. Min Act: -0.0000

Data Index: 1590558 (The Pile)

Max Activating Token Index: 466