Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3327 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5907. Min Act: -0.0002

Data Index: 1309710 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5860. Min Act: -0.0001

Data Index: 1184219 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4827. Min Act: -0.0002

Data Index: 1256543 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4890. Min Act: -0.0001

Data Index: 736158 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5444. Min Act: -0.0001

Data Index: 1146157 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4584. Min Act: -0.0002

Data Index: 1093283 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4886. Min Act: -0.0002

Data Index: 859317 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4789. Min Act: -0.0002

Data Index: 353183 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4528. Min Act: -0.0002

Data Index: 333080 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4612. Min Act: -0.0002

Data Index: 693947 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4192. Min Act: -0.0002

Data Index: 91385 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4685. Min Act: -0.0002

Data Index: 787422 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4776. Min Act: -0.0002

Data Index: 19482 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4746. Min Act: -0.0002

Data Index: 1146622 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4277. Min Act: -0.0002

Data Index: 674496 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4669. Min Act: -0.0002

Data Index: 873771 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3824. Min Act: -0.0002

Data Index: 578669 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4324. Min Act: -0.0001

Data Index: 92661 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4341. Min Act: -0.0002

Data Index: 334032 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3896. Min Act: -0.0002

Data Index: 1313356 (C4 (Web Text))

Max Activating Token Index: 827