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

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

Neuron 1203 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2162. Min Range: -7.2162

Max Act: 7.2162. Min Act: -0.0000

Data Index: 163074 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 7.2162. Min Range: -7.2162

Max Act: 6.9876. Min Act: -0.0000

Data Index: 1651032 (Python Code)

Max Activating Token Index: 221

Text #2

Max Range: 7.2162. Min Range: -7.2162

Max Act: 7.1130. Min Act: -0.0000

Data Index: 803209 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 7.2162. Min Range: -7.2162

Max Act: 6.6928. Min Act: -0.0000

Data Index: 1349396 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 7.2162. Min Range: -7.2162

Max Act: 6.4852. Min Act: -0.0000

Data Index: 249680 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 7.2162. Min Range: -7.2162

Max Act: 6.2721. Min Act: -0.0000

Data Index: 838672 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 7.2162. Min Range: -7.2162

Max Act: 6.2903. Min Act: -0.0000

Data Index: 1555430 (Python Code)

Max Activating Token Index: 493

Text #7

Max Range: 7.2162. Min Range: -7.2162

Max Act: 6.4928. Min Act: -0.0000

Data Index: 44598 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 7.2162. Min Range: -7.2162

Max Act: 5.7793. Min Act: -0.0000

Data Index: 1196336 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 7.2162. Min Range: -7.2162

Max Act: 6.0789. Min Act: -0.0000

Data Index: 229595 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 7.2162. Min Range: -7.2162

Max Act: 5.8898. Min Act: -0.0000

Data Index: 354298 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 7.2162. Min Range: -7.2162

Max Act: 5.8505. Min Act: -0.0000

Data Index: 974897 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 7.2162. Min Range: -7.2162

Max Act: 5.9656. Min Act: -0.0000

Data Index: 1062653 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 7.2162. Min Range: -7.2162

Max Act: 5.6872. Min Act: -0.0000

Data Index: 1104087 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 7.2162. Min Range: -7.2162

Max Act: 5.5408. Min Act: -0.0000

Data Index: 755094 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 7.2162. Min Range: -7.2162

Max Act: 5.5150. Min Act: -0.0000

Data Index: 764032 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 7.2162. Min Range: -7.2162

Max Act: 5.4844. Min Act: -0.0000

Data Index: 360586 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 7.2162. Min Range: -7.2162

Max Act: 5.4737. Min Act: -0.0000

Data Index: 630038 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 7.2162. Min Range: -7.2162

Max Act: 5.4524. Min Act: -0.0000

Data Index: 246970 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 7.2162. Min Range: -7.2162

Max Act: 5.1825. Min Act: -0.0000

Data Index: 422279 (C4 (Web Text))

Max Activating Token Index: 597