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

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

Neuron 3551 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: 1.4817. Min Range: -1.4817

Max Act: 1.4817. Min Act: -0.0002

Data Index: 1061177 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.4620. Min Act: -0.0002

Data Index: 748815 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.4245. Min Act: -0.0002

Data Index: 614527 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.4303. Min Act: -0.0003

Data Index: 962488 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.4245. Min Act: -0.0002

Data Index: 1259366 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.3663. Min Act: -0.0002

Data Index: 943815 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.3165. Min Act: -0.0002

Data Index: 509940 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.3259. Min Act: -0.0002

Data Index: 915464 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.3317. Min Act: -0.0002

Data Index: 709674 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.3171. Min Act: -0.0002

Data Index: 1082346 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.2914. Min Act: -0.0002

Data Index: 277508 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.3164. Min Act: -0.0002

Data Index: 957802 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.2768. Min Act: -0.0002

Data Index: 1136636 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.3073. Min Act: -0.0003

Data Index: 897850 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.2978. Min Act: -0.0002

Data Index: 37972 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.2863. Min Act: -0.0002

Data Index: 1339984 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.3055. Min Act: -0.0002

Data Index: 1304666 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.2921. Min Act: -0.0002

Data Index: 674522 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.2692. Min Act: -0.0002

Data Index: 482146 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.2639. Min Act: -0.0002

Data Index: 837727 (C4 (Web Text))

Max Activating Token Index: 165