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

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

Neuron 4408 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: 5.0738. Min Range: -5.0738

Max Act: 5.0738. Min Act: 0.0000

Data Index: 212816 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 5.0738. Min Range: -5.0738

Max Act: 4.7210. Min Act: -0.0000

Data Index: 45458 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 5.0738. Min Range: -5.0738

Max Act: 4.4926. Min Act: 0.0000

Data Index: 377636 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 5.0738. Min Range: -5.0738

Max Act: 3.7710. Min Act: 0.0001

Data Index: 1290899 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 5.0738. Min Range: -5.0738

Max Act: 3.6649. Min Act: -0.0000

Data Index: 24077 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 5.0738. Min Range: -5.0738

Max Act: 3.6281. Min Act: -0.0000

Data Index: 1128649 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 5.0738. Min Range: -5.0738

Max Act: 3.4072. Min Act: 0.0000

Data Index: 523894 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 5.0738. Min Range: -5.0738

Max Act: 3.6846. Min Act: 0.0001

Data Index: 1034022 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 5.0738. Min Range: -5.0738

Max Act: 3.3636. Min Act: -0.0000

Data Index: 1142663 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 5.0738. Min Range: -5.0738

Max Act: 3.1377. Min Act: -0.0000

Data Index: 102903 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 5.0738. Min Range: -5.0738

Max Act: 3.1118. Min Act: -0.0000

Data Index: 603400 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 5.0738. Min Range: -5.0738

Max Act: 2.8882. Min Act: -0.0000

Data Index: 325273 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 5.0738. Min Range: -5.0738

Max Act: 2.9899. Min Act: -0.0000

Data Index: 480225 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 5.0738. Min Range: -5.0738

Max Act: 2.9872. Min Act: -0.0000

Data Index: 1322944 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 5.0738. Min Range: -5.0738

Max Act: 2.8130. Min Act: -0.0000

Data Index: 952586 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 5.0738. Min Range: -5.0738

Max Act: 2.9008. Min Act: -0.0000

Data Index: 757341 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 5.0738. Min Range: -5.0738

Max Act: 2.6299. Min Act: -0.0000

Data Index: 162446 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 5.0738. Min Range: -5.0738

Max Act: 2.5854. Min Act: -0.0000

Data Index: 444840 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 5.0738. Min Range: -5.0738

Max Act: 2.5760. Min Act: -0.0000

Data Index: 963151 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 5.0738. Min Range: -5.0738

Max Act: 2.5483. Min Act: -0.0000

Data Index: 321699 (C4 (Web Text))

Max Activating Token Index: 331