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

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

Neuron 2674 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.9208. Min Act: -0.0000

Data Index: 780429 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.6414. Min Act: -0.0000

Data Index: 197010 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.6917. Min Act: -0.0001

Data Index: 331523 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.7055. Min Act: -0.0001

Data Index: 565833 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.6600. Min Act: -0.0000

Data Index: 661765 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.6738. Min Act: -0.0000

Data Index: 24714 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.7066. Min Act: -0.0001

Data Index: 1213087 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.6231. Min Act: -0.0000

Data Index: 512830 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1050969 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.5532. Min Act: -0.0000

Data Index: 322330 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.5506. Min Act: -0.0000

Data Index: 206388 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.6436. Min Act: -0.0001

Data Index: 985906 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.5668. Min Act: -0.0000

Data Index: 56608 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.6216. Min Act: -0.0000

Data Index: 865385 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.6353. Min Act: -0.0000

Data Index: 179667 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.4920. Min Act: -0.0000

Data Index: 746638 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.5631. Min Act: -0.0001

Data Index: 1455351 (Python Code)

Max Activating Token Index: 482

Text #17

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.5433. Min Act: -0.0000

Data Index: 704981 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1033854 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.9208. Min Range: -0.9208

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1300238 (C4 (Web Text))

Max Activating Token Index: 636