Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4551 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.8404. Min Act: -0.0000

Data Index: 1630052 (The Pile)

Max Activating Token Index: 253

Text #1

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.6735. Min Act: -0.0000

Data Index: 629800 (The Pile)

Max Activating Token Index: 446

Text #2

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.7255. Min Act: -0.0000

Data Index: 623996 (The Pile)

Max Activating Token Index: 139

Text #3

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5623. Min Act: -0.0000

Data Index: 768092 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.7405. Min Act: -0.0000

Data Index: 1786464 (The Pile)

Max Activating Token Index: 369

Text #5

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5925. Min Act: -0.0000

Data Index: 1459996 (The Pile)

Max Activating Token Index: 919

Text #6

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3798. Min Act: -0.0000

Data Index: 1241836 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5673. Min Act: -0.0000

Data Index: 1639796 (The Pile)

Max Activating Token Index: 100

Text #8

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.6308. Min Act: -0.0000

Data Index: 1584574 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3851. Min Act: 0.0000

Data Index: 307580 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4586. Min Act: -0.0000

Data Index: 1905224 (The Pile)

Max Activating Token Index: 505

Text #11

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4318. Min Act: -0.0000

Data Index: 52440 (The Pile)

Max Activating Token Index: 542

Text #12

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4276. Min Act: -0.0000

Data Index: 1350368 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4088. Min Act: -0.0000

Data Index: 300350 (The Pile)

Max Activating Token Index: 326

Text #14

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4147. Min Act: -0.0000

Data Index: 331461 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5127. Min Act: -0.0000

Data Index: 918318 (The Pile)

Max Activating Token Index: 153

Text #16

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4122. Min Act: -0.0000

Data Index: 1936685 (The Pile)

Max Activating Token Index: 520

Text #17

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3168. Min Act: -0.0000

Data Index: 202639 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3152. Min Act: -0.0000

Data Index: 997411 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4653. Min Act: -0.0000

Data Index: 446471 (The Pile)

Max Activating Token Index: 619