Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3125 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1036769 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1306634 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1295628 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.4640. Min Act: -0.0000

Data Index: 163710 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.5662. Min Act: -0.0000

Data Index: 676537 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.5061. Min Act: -0.0000

Data Index: 809542 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.4704. Min Act: -0.0000

Data Index: 195524 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.4932. Min Act: -0.0000

Data Index: 492758 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1050101 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1326614 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.4479. Min Act: -0.0000

Data Index: 624483 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.4841. Min Act: -0.0000

Data Index: 555009 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.5210. Min Act: -0.0000

Data Index: 25893 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.4984. Min Act: -0.0000

Data Index: 264504 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.4769. Min Act: -0.0000

Data Index: 761303 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.4492. Min Act: -0.0000

Data Index: 989385 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.4207. Min Act: -0.0000

Data Index: 586025 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.4592. Min Act: -0.0000

Data Index: 517458 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.4269. Min Act: -0.0000

Data Index: 755775 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.7728. Min Range: -0.7728

Max Act: 0.4352. Min Act: -0.0000

Data Index: 531059 (C4 (Web Text))

Max Activating Token Index: 75