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

Dataset: The Pile

Neuron 210 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: 4.7778. Min Range: -4.7778

Max Act: 4.7778. Min Act: -0.0000

Data Index: 133506 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 4.7778. Min Range: -4.7778

Max Act: 4.5593. Min Act: -0.0000

Data Index: 1528539 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 4.7778. Min Range: -4.7778

Max Act: 4.5869. Min Act: -0.0000

Data Index: 923374 (The Pile)

Max Activating Token Index: 320

Text #3

Max Range: 4.7778. Min Range: -4.7778

Max Act: 4.4220. Min Act: -0.0000

Data Index: 1366591 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 4.7778. Min Range: -4.7778

Max Act: 4.0578. Min Act: -0.0000

Data Index: 486488 (The Pile)

Max Activating Token Index: 49

Text #5

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.5456. Min Act: -0.0000

Data Index: 1270307 (The Pile)

Max Activating Token Index: 517

Text #6

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.7565. Min Act: -0.0000

Data Index: 1727325 (The Pile)

Max Activating Token Index: 354

Text #7

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.3770. Min Act: -0.0000

Data Index: 794015 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.9522. Min Act: -0.0000

Data Index: 1776249 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.5745. Min Act: -0.0000

Data Index: 667719 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.5337. Min Act: -0.0000

Data Index: 851141 (The Pile)

Max Activating Token Index: 89

Text #11

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.6409. Min Act: -0.0000

Data Index: 1773943 (The Pile)

Max Activating Token Index: 123

Text #12

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.5814. Min Act: -0.0000

Data Index: 1027215 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.3313. Min Act: -0.0000

Data Index: 73588 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.2143. Min Act: -0.0000

Data Index: 1013417 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.5391. Min Act: -0.0000

Data Index: 1574658 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.5591. Min Act: -0.0000

Data Index: 1358398 (The Pile)

Max Activating Token Index: 220

Text #17

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.6901. Min Act: -0.0000

Data Index: 557454 (The Pile)

Max Activating Token Index: 24

Text #18

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.3423. Min Act: -0.0000

Data Index: 1318545 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.5513. Min Act: -0.0000

Data Index: 1017302 (The Pile)

Max Activating Token Index: 811