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

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

Neuron 4829 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3597. Min Range: -5.3597

Max Act: 5.3597. Min Act: -0.0000

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 5.3597. Min Range: -5.3597

Max Act: 4.9067. Min Act: -0.0000

Data Index: 1357085 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 5.3597. Min Range: -5.3597

Max Act: 4.4769. Min Act: -0.0000

Data Index: 675139 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 5.3597. Min Range: -5.3597

Max Act: 4.3525. Min Act: -0.0000

Data Index: 1209520 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 5.3597. Min Range: -5.3597

Max Act: 4.4767. Min Act: -0.0000

Data Index: 280806 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 5.3597. Min Range: -5.3597

Max Act: 4.3439. Min Act: -0.0000

Data Index: 385145 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.9698. Min Act: -0.0000

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.8455. Min Act: -0.0000

Data Index: 1417346 (Python Code)

Max Activating Token Index: 879

Text #8

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.5898. Min Act: -0.0000

Data Index: 356495 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.5299. Min Act: -0.0000

Data Index: 1638134 (Python Code)

Max Activating Token Index: 822

Text #10

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.6790. Min Act: -0.0000

Data Index: 1282662 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.4560. Min Act: -0.0000

Data Index: 691366 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.6077. Min Act: -0.0000

Data Index: 648739 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.5992. Min Act: -0.0000

Data Index: 592295 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.5745. Min Act: -0.0000

Data Index: 991146 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.5502. Min Act: -0.0000

Data Index: 1490555 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.5311. Min Act: -0.0000

Data Index: 1540309 (Python Code)

Max Activating Token Index: 659

Text #17

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.3552. Min Act: -0.0000

Data Index: 502362 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.3499. Min Act: -0.0000

Data Index: 584628 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 5.3597. Min Range: -5.3597

Max Act: 3.3196. Min Act: -0.0000

Data Index: 464962 (C4 (Web Text))

Max Activating Token Index: 666