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

Dataset: The Pile

Neuron 728 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4680. Min Act: -0.0000

Data Index: 859376 (The Pile)

Max Activating Token Index: 698

Text #1

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1231682 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4558. Min Act: -0.0000

Data Index: 20184 (The Pile)

Max Activating Token Index: 617

Text #3

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1502461 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4166. Min Act: -0.0000

Data Index: 751625 (The Pile)

Max Activating Token Index: 523

Text #5

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4418. Min Act: -0.0000

Data Index: 707115 (The Pile)

Max Activating Token Index: 16

Text #6

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4242. Min Act: -0.0000

Data Index: 561438 (The Pile)

Max Activating Token Index: 235

Text #7

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3950. Min Act: -0.0000

Data Index: 787153 (The Pile)

Max Activating Token Index: 180

Text #8

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4002. Min Act: -0.0000

Data Index: 633447 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1985313 (The Pile)

Max Activating Token Index: 463

Text #10

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1136567 (The Pile)

Max Activating Token Index: 53

Text #11

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4041. Min Act: -0.0000

Data Index: 214148 (The Pile)

Max Activating Token Index: 356

Text #12

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4159. Min Act: -0.0000

Data Index: 134399 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3856. Min Act: -0.0000

Data Index: 204192 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4121. Min Act: -0.0000

Data Index: 1008938 (The Pile)

Max Activating Token Index: 743

Text #15

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3818. Min Act: -0.0000

Data Index: 755184 (The Pile)

Max Activating Token Index: 20

Text #16

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3951. Min Act: -0.0000

Data Index: 698871 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1956067 (The Pile)

Max Activating Token Index: 482

Text #18

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1799356 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3790. Min Act: -0.0000

Data Index: 83082 (The Pile)

Max Activating Token Index: 118