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

Dataset: The Pile

Neuron 2700 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: 1.1107. Min Range: -1.1107

Max Act: 1.1107. Min Act: -0.0000

Data Index: 899012 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9834. Min Act: -0.0000

Data Index: 1041705 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9012. Min Act: -0.0000

Data Index: 774111 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0041. Min Act: -0.0000

Data Index: 967216 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1739160 (The Pile)

Max Activating Token Index: 255

Text #5

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0827. Min Act: -0.0000

Data Index: 1274339 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8574. Min Act: -0.0000

Data Index: 743455 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1998840 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8909. Min Act: -0.0000

Data Index: 1655614 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8622. Min Act: -0.0000

Data Index: 318141 (The Pile)

Max Activating Token Index: 475

Text #10

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8603. Min Act: -0.0000

Data Index: 762823 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1429470 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9645. Min Act: -0.0000

Data Index: 883633 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9010. Min Act: -0.0000

Data Index: 464599 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9570. Min Act: -0.0000

Data Index: 923061 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1924206 (The Pile)

Max Activating Token Index: 130

Text #16

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1528859 (The Pile)

Max Activating Token Index: 441

Text #17

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1235056 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1274536 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1330514 (The Pile)

Max Activating Token Index: 926