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

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

Neuron 5162 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.8132. Min Act: -0.0002

Data Index: 491220 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.8102. Min Act: -0.0002

Data Index: 311010 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.8126. Min Act: -0.0002

Data Index: 1136820 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.7282. Min Act: -0.0003

Data Index: 1224379 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.6825. Min Act: -0.0002

Data Index: 442504 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.7036. Min Act: -0.0002

Data Index: 287977 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.6730. Min Act: -0.0002

Data Index: 218929 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.7077. Min Act: -0.0002

Data Index: 119773 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.6804. Min Act: -0.0002

Data Index: 288657 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.6491. Min Act: -0.0002

Data Index: 1224474 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.6423. Min Act: -0.0002

Data Index: 110392 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.6100. Min Act: -0.0002

Data Index: 797541 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5621. Min Act: -0.0002

Data Index: 491840 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.6358. Min Act: -0.0002

Data Index: 1077656 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5850. Min Act: -0.0002

Data Index: 1095829 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5678. Min Act: -0.0002

Data Index: 536790 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5503. Min Act: -0.0002

Data Index: 189457 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.6117. Min Act: -0.0002

Data Index: 1052587 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5407. Min Act: -0.0002

Data Index: 6657 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.8132. Min Range: -1.8132

Max Act: 1.5688. Min Act: -0.0002

Data Index: 172250 (C4 (Web Text))

Max Activating Token Index: 939