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

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

Neuron 4498 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: 1.4459. Min Range: -1.4459

Max Act: 1.4459. Min Act: -0.0002

Data Index: 866410 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.3221. Min Act: -0.0002

Data Index: 736768 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.2858. Min Act: -0.0002

Data Index: 126253 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.2761. Min Act: -0.0002

Data Index: 1235768 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.2836. Min Act: -0.0002

Data Index: 626135 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.2841. Min Act: -0.0002

Data Index: 968411 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.2485. Min Act: -0.0002

Data Index: 402636 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.1761. Min Act: -0.0003

Data Index: 1302556 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.1673. Min Act: -0.0002

Data Index: 686359 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.1686. Min Act: -0.0002

Data Index: 90457 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.1738. Min Act: -0.0002

Data Index: 699457 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.1348. Min Act: -0.0002

Data Index: 866137 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.1434. Min Act: -0.0002

Data Index: 160902 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.1387. Min Act: -0.0002

Data Index: 521117 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.1313. Min Act: -0.0002

Data Index: 925822 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.1233. Min Act: -0.0002

Data Index: 171165 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.1208. Min Act: -0.0002

Data Index: 1161106 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.1144. Min Act: -0.0002

Data Index: 540480 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.0840. Min Act: -0.0002

Data Index: 960598 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 1.4459. Min Range: -1.4459

Max Act: 1.0799. Min Act: -0.0002

Data Index: 223913 (C4 (Web Text))

Max Activating Token Index: 117