Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4576 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.3187. Min Act: -0.0003

Data Index: 73559 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.3089. Min Act: -0.0003

Data Index: 1259875 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2816. Min Act: -0.0003

Data Index: 670572 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2907. Min Act: -0.0003

Data Index: 88356 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2834. Min Act: -0.0003

Data Index: 247837 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2811. Min Act: -0.0003

Data Index: 485145 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2697. Min Act: -0.0003

Data Index: 982875 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2684. Min Act: -0.0003

Data Index: 1227498 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2652. Min Act: -0.0003

Data Index: 235561 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2741. Min Act: -0.0003

Data Index: 1351337 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2442. Min Act: -0.0003

Data Index: 784820 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2597. Min Act: -0.0003

Data Index: 151266 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2472. Min Act: -0.0003

Data Index: 1125312 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2434. Min Act: -0.0003

Data Index: 112834 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2455. Min Act: -0.0003

Data Index: 16639 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2486. Min Act: -0.0003

Data Index: 240278 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2382. Min Act: -0.0003

Data Index: 153063 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2463. Min Act: -0.0003

Data Index: 1004013 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2377. Min Act: -0.0003

Data Index: 107040 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2338. Min Act: -0.0003

Data Index: 1039779 (C4 (Web Text))

Max Activating Token Index: 473