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

Dataset: The Pile

Neuron 2096 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1625842 (The Pile)

Max Activating Token Index: 402

Text #1

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.2895. Min Act: -0.0000

Data Index: 1819525 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.3371. Min Act: -0.0000

Data Index: 1638846 (The Pile)

Max Activating Token Index: 374

Text #3

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1524992 (The Pile)

Max Activating Token Index: 140

Text #4

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.2589. Min Act: -0.0000

Data Index: 1448519 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1861913 (The Pile)

Max Activating Token Index: 221

Text #6

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1249. Min Act: -0.0000

Data Index: 1313971 (The Pile)

Max Activating Token Index: 110

Text #7

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1882. Min Act: -0.0000

Data Index: 624592 (The Pile)

Max Activating Token Index: 191

Text #8

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1544. Min Act: -0.0000

Data Index: 403878 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0783. Min Act: -0.0000

Data Index: 981643 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0776. Min Act: -0.0000

Data Index: 1010833 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1318. Min Act: -0.0000

Data Index: 1136234 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1925751 (The Pile)

Max Activating Token Index: 75

Text #13

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0946. Min Act: -0.0000

Data Index: 856679 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.2213. Min Act: -0.0000

Data Index: 16418 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0541. Min Act: -0.0000

Data Index: 1056382 (The Pile)

Max Activating Token Index: 73

Text #16

Max Range: 1.3682. Min Range: -1.3682

Max Act: 0.9320. Min Act: -0.0000

Data Index: 1794513 (The Pile)

Max Activating Token Index: 80

Text #17

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1420. Min Act: -0.0000

Data Index: 419347 (The Pile)

Max Activating Token Index: 390

Text #18

Max Range: 1.3682. Min Range: -1.3682

Max Act: 0.9876. Min Act: -0.0000

Data Index: 590525 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 1.3682. Min Range: -1.3682

Max Act: 0.9059. Min Act: -0.0000

Data Index: 961790 (The Pile)

Max Activating Token Index: 544