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

Dataset: The Pile

Neuron 3264 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: 0.8497. Min Range: -0.8497

Max Act: 0.8497. Min Act: -0.0000

Data Index: 108481 (The Pile)

Max Activating Token Index: 406

Text #1

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1232047 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6432. Min Act: -0.0000

Data Index: 287335 (The Pile)

Max Activating Token Index: 688

Text #3

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6535. Min Act: -0.0000

Data Index: 710252 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6952. Min Act: -0.0000

Data Index: 638463 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6681. Min Act: -0.0000

Data Index: 4166 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1688840 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6189. Min Act: -0.0000

Data Index: 343440 (The Pile)

Max Activating Token Index: 750

Text #8

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5963. Min Act: -0.0000

Data Index: 346672 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1568682 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5960. Min Act: -0.0000

Data Index: 52734 (The Pile)

Max Activating Token Index: 182

Text #11

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5714. Min Act: -0.0000

Data Index: 946199 (The Pile)

Max Activating Token Index: 680

Text #12

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1256447 (The Pile)

Max Activating Token Index: 239

Text #13

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1595156 (The Pile)

Max Activating Token Index: 153

Text #14

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5758. Min Act: 0.0000

Data Index: 369264 (The Pile)

Max Activating Token Index: 493

Text #15

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5105. Min Act: -0.0000

Data Index: 361310 (The Pile)

Max Activating Token Index: 805

Text #16

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1574265 (The Pile)

Max Activating Token Index: 542

Text #17

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5341. Min Act: -0.0000

Data Index: 698612 (The Pile)

Max Activating Token Index: 108

Text #18

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5066. Min Act: -0.0000

Data Index: 70126 (The Pile)

Max Activating Token Index: 128

Text #19

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1759608 (The Pile)

Max Activating Token Index: 821