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

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

Neuron 520 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: 3.1756. Min Range: -3.1756

Max Act: 3.1756. Min Act: -0.0000

Data Index: 1139014 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0344. Min Act: -0.0000

Data Index: 444350 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.8993. Min Act: -0.0000

Data Index: 906234 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.8455. Min Act: -0.0000

Data Index: 1000296 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.7257. Min Act: -0.0000

Data Index: 512572 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.8573. Min Act: -0.0000

Data Index: 1358291 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.6775. Min Act: -0.0000

Data Index: 646082 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.6411. Min Act: -0.0000

Data Index: 932422 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.4008. Min Act: -0.0000

Data Index: 535692 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.5273. Min Act: -0.0000

Data Index: 118638 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.5022. Min Act: -0.0000

Data Index: 751118 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.3494. Min Act: -0.0000

Data Index: 1124718 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.4156. Min Act: -0.0000

Data Index: 1312993 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.3637. Min Act: -0.0000

Data Index: 875116 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.1996. Min Act: -0.0000

Data Index: 1333798 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.1968. Min Act: -0.0000

Data Index: 793626 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.2565. Min Act: -0.0000

Data Index: 202568 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.2802. Min Act: -0.0000

Data Index: 809832 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.1312. Min Act: -0.0000

Data Index: 314497 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 3.1756. Min Range: -3.1756

Max Act: 2.2534. Min Act: -0.0000

Data Index: 985172 (C4 (Web Text))

Max Activating Token Index: 505