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

Dataset: The Pile

Neuron 4288 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.6828. Min Act: -0.0000

Data Index: 1518087 (The Pile)

Max Activating Token Index: 414

Text #1

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.5867. Min Act: -0.0000

Data Index: 1511372 (The Pile)

Max Activating Token Index: 72

Text #2

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.6078. Min Act: -0.0000

Data Index: 1751702 (The Pile)

Max Activating Token Index: 903

Text #3

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.7758. Min Act: -0.0000

Data Index: 1365595 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.6908. Min Act: -0.0000

Data Index: 878673 (The Pile)

Max Activating Token Index: 101

Text #5

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.6760. Min Act: -0.0000

Data Index: 345052 (The Pile)

Max Activating Token Index: 58

Text #6

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.5768. Min Act: -0.0000

Data Index: 875250 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.4920. Min Act: -0.0000

Data Index: 211747 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.5820. Min Act: -0.0000

Data Index: 1285485 (The Pile)

Max Activating Token Index: 830

Text #9

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.5898. Min Act: -0.0000

Data Index: 397725 (The Pile)

Max Activating Token Index: 841

Text #10

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.5570. Min Act: -0.0000

Data Index: 300271 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.3685. Min Act: -0.0000

Data Index: 1366996 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.4228. Min Act: -0.0000

Data Index: 1438140 (The Pile)

Max Activating Token Index: 273

Text #13

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.5382. Min Act: -0.0000

Data Index: 1107392 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.3536. Min Act: -0.0000

Data Index: 1040793 (The Pile)

Max Activating Token Index: 924

Text #15

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.5192. Min Act: -0.0000

Data Index: 1762215 (The Pile)

Max Activating Token Index: 74

Text #16

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.5312. Min Act: -0.0000

Data Index: 751193 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.4814. Min Act: -0.0000

Data Index: 1219462 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.5034. Min Act: -0.0000

Data Index: 1466619 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 1.7758. Min Range: -1.7758

Max Act: 1.6017. Min Act: -0.0000

Data Index: 744125 (The Pile)

Max Activating Token Index: 498