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

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

Neuron 2415 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: 3.8537. Min Range: -3.8537

Max Act: 3.8537. Min Act: -0.0000

Data Index: 1338871 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.6134. Min Act: -0.0000

Data Index: 458247 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.6039. Min Act: -0.0000

Data Index: 188883 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.7291. Min Act: -0.0000

Data Index: 920414 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.5735. Min Act: -0.0000

Data Index: 82099 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.6016. Min Act: -0.0000

Data Index: 358894 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.6112. Min Act: -0.0000

Data Index: 78930 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.7432. Min Act: -0.0000

Data Index: 761944 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.4151. Min Act: -0.0000

Data Index: 779533 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.6657. Min Act: -0.0000

Data Index: 754414 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.3214. Min Act: -0.0000

Data Index: 268553 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.7642. Min Act: -0.0000

Data Index: 528736 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.2840. Min Act: -0.0000

Data Index: 466805 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.2689. Min Act: -0.0000

Data Index: 251793 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.5507. Min Act: -0.0000

Data Index: 938861 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.1921. Min Act: -0.0000

Data Index: 1306471 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.2830. Min Act: -0.0000

Data Index: 222208 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.1357. Min Act: -0.0000

Data Index: 306878 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 3.8537. Min Range: -3.8537

Max Act: 2.9744. Min Act: -0.0000

Data Index: 952089 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 3.8537. Min Range: -3.8537

Max Act: 3.1050. Min Act: -0.0000

Data Index: 831532 (C4 (Web Text))

Max Activating Token Index: 978