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

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

Neuron 2568 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: 1.1169. Min Range: -1.1169

Max Act: 1.1169. Min Act: -0.0002

Data Index: 834081 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.1169. Min Range: -1.1169

Max Act: 1.0893. Min Act: -0.0002

Data Index: 66419 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 1.1169. Min Range: -1.1169

Max Act: 1.0158. Min Act: -0.0003

Data Index: 664624 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 1.1169. Min Range: -1.1169

Max Act: 1.0118. Min Act: -0.0002

Data Index: 71956 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9813. Min Act: -0.0002

Data Index: 335117 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9999. Min Act: -0.0002

Data Index: 1315134 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9830. Min Act: -0.0002

Data Index: 68909 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9639. Min Act: -0.0002

Data Index: 769918 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9267. Min Act: -0.0002

Data Index: 1268130 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9179. Min Act: -0.0002

Data Index: 912974 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9180. Min Act: -0.0002

Data Index: 583615 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9157. Min Act: -0.0002

Data Index: 243075 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9205. Min Act: -0.0002

Data Index: 448559 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9011. Min Act: -0.0003

Data Index: 897177 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9019. Min Act: -0.0003

Data Index: 188555 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9092. Min Act: -0.0003

Data Index: 1303371 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.8871. Min Act: -0.0002

Data Index: 317027 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.8837. Min Act: -0.0002

Data Index: 481416 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.8902. Min Act: -0.0002

Data Index: 604645 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.8955. Min Act: -0.0002

Data Index: 725352 (C4 (Web Text))

Max Activating Token Index: 978