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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 805 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0759. Min Range: -1.0759

Max Act: 1.0120. Min Act: -0.0000

Data Index: 372720 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 1.0759. Min Range: -1.0759

Max Act: 1.0363. Min Act: -0.0000

Data Index: 702630 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9443. Min Act: -0.0000

Data Index: 988709 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 1.0759. Min Range: -1.0759

Max Act: 1.0759. Min Act: -0.0000

Data Index: 104616 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9369. Min Act: -0.0000

Data Index: 51151 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9230. Min Act: -0.0000

Data Index: 628210 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8464. Min Act: -0.0000

Data Index: 378313 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8683. Min Act: -0.0000

Data Index: 474147 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8913. Min Act: -0.0000

Data Index: 416466 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8565. Min Act: -0.0000

Data Index: 888012 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7624. Min Act: -0.0000

Data Index: 836966 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8150. Min Act: -0.0000

Data Index: 162994 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1219712 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7468. Min Act: -0.0000

Data Index: 1025733 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7231. Min Act: -0.0000

Data Index: 849400 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7865. Min Act: -0.0000

Data Index: 499918 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8273. Min Act: -0.0000

Data Index: 91924 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7759. Min Act: -0.0000

Data Index: 780951 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1010353 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8096. Min Act: -0.0000

Data Index: 1277261 (C4 (Web Text))

Max Activating Token Index: 927