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

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

Neuron 971 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.6233. Min Act: -0.0000

Data Index: 1478115 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.3095. Min Act: -0.0000

Data Index: 1368871 (Python Code)

Max Activating Token Index: 150

Text #2

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.0800. Min Act: -0.0000

Data Index: 538835 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.5234. Min Act: -0.0000

Data Index: 1503514 (Python Code)

Max Activating Token Index: 254

Text #4

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.6254. Min Act: -0.0000

Data Index: 1297137 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.7022. Min Act: -0.0000

Data Index: 546686 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.3739. Min Act: -0.0000

Data Index: 277383 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.4714. Min Act: -0.0000

Data Index: 1522260 (Python Code)

Max Activating Token Index: 137

Text #8

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.5647. Min Act: -0.0000

Data Index: 665581 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.2753. Min Act: -0.0000

Data Index: 1572930 (Python Code)

Max Activating Token Index: 320

Text #10

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.3823. Min Act: -0.0000

Data Index: 1382205 (Python Code)

Max Activating Token Index: 546

Text #11

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.3488. Min Act: -0.0000

Data Index: 1481659 (Python Code)

Max Activating Token Index: 588

Text #12

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.2217. Min Act: -0.0000

Data Index: 1652520 (Python Code)

Max Activating Token Index: 748

Text #13

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.2859. Min Act: -0.0000

Data Index: 1514601 (Python Code)

Max Activating Token Index: 256

Text #14

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.1917. Min Act: -0.0000

Data Index: 1500950 (Python Code)

Max Activating Token Index: 252

Text #15

Max Range: 3.6233. Min Range: -3.6233

Max Act: 1.9892. Min Act: -0.0000

Data Index: 1123504 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 3.6233. Min Range: -3.6233

Max Act: 1.9672. Min Act: -0.0000

Data Index: 1625337 (Python Code)

Max Activating Token Index: 974

Text #17

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.0656. Min Act: -0.0000

Data Index: 1579556 (Python Code)

Max Activating Token Index: 164

Text #18

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.0482. Min Act: -0.0000

Data Index: 1480433 (Python Code)

Max Activating Token Index: 84

Text #19

Max Range: 3.6233. Min Range: -3.6233

Max Act: 1.9690. Min Act: -0.0000

Data Index: 1594929 (Python Code)

Max Activating Token Index: 730