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

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

Neuron 4182 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9357. Min Range: -4.9357

Max Act: 4.9357. Min Act: -0.0000

Data Index: 1255645 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 4.9357. Min Range: -4.9357

Max Act: 4.6535. Min Act: -0.0000

Data Index: 281519 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 4.9357. Min Range: -4.9357

Max Act: 4.0444. Min Act: -0.0000

Data Index: 544284 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.9507. Min Act: -0.0000

Data Index: 1104211 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.6169. Min Act: -0.0000

Data Index: 280100 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.8197. Min Act: -0.0000

Data Index: 30086 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.6336. Min Act: -0.0000

Data Index: 713604 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.5477. Min Act: -0.0000

Data Index: 939113 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.4344. Min Act: -0.0000

Data Index: 577963 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.3813. Min Act: -0.0000

Data Index: 372315 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.3405. Min Act: -0.0000

Data Index: 1105465 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.3120. Min Act: -0.0000

Data Index: 703636 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.2986. Min Act: -0.0000

Data Index: 651298 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.4219. Min Act: -0.0000

Data Index: 1190497 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.2405. Min Act: -0.0000

Data Index: 282898 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.2140. Min Act: -0.0000

Data Index: 1336705 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.1655. Min Act: -0.0000

Data Index: 1083820 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.1437. Min Act: -0.0000

Data Index: 789848 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 4.9357. Min Range: -4.9357

Max Act: 3.1382. Min Act: -0.0000

Data Index: 179782 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 4.9357. Min Range: -4.9357

Max Act: 2.9848. Min Act: -0.0000

Data Index: 469457 (C4 (Web Text))

Max Activating Token Index: 1002