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

Dataset: The Pile

Neuron 1545 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: 1.9749. Min Range: -1.9749

Max Act: 1.8587. Min Act: -0.0000

Data Index: 1963821 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.9668. Min Act: -0.0000

Data Index: 1128762 (The Pile)

Max Activating Token Index: 574

Text #2

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.9749. Min Act: -0.0000

Data Index: 669055 (The Pile)

Max Activating Token Index: 531

Text #3

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6870. Min Act: -0.0000

Data Index: 205803 (The Pile)

Max Activating Token Index: 570

Text #4

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6692. Min Act: -0.0000

Data Index: 1729494 (The Pile)

Max Activating Token Index: 415

Text #5

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1678502 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.7494. Min Act: -0.0000

Data Index: 1502393 (The Pile)

Max Activating Token Index: 488

Text #7

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.7438. Min Act: -0.0000

Data Index: 1067818 (The Pile)

Max Activating Token Index: 1014

Text #8

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.4042. Min Act: -0.0000

Data Index: 167352 (The Pile)

Max Activating Token Index: 885

Text #9

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6574. Min Act: -0.0000

Data Index: 1987442 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.5463. Min Act: -0.0000

Data Index: 234597 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.4908. Min Act: -0.0000

Data Index: 1363023 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.5218. Min Act: -0.0000

Data Index: 608080 (The Pile)

Max Activating Token Index: 5

Text #13

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.5560. Min Act: -0.0000

Data Index: 1261376 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.5091. Min Act: -0.0000

Data Index: 228961 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.5124. Min Act: -0.0000

Data Index: 1384365 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.5385. Min Act: -0.0000

Data Index: 879123 (The Pile)

Max Activating Token Index: 332

Text #17

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.4877. Min Act: -0.0000

Data Index: 772532 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6424. Min Act: -0.0000

Data Index: 1518430 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.4710. Min Act: -0.0000

Data Index: 702828 (The Pile)

Max Activating Token Index: 433