Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 2046 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1507961 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0404. Min Act: -0.0003

Data Index: 919793 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0397. Min Act: -0.0003

Data Index: 669539 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1217888 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1462328 (Python Code)

Max Activating Token Index: 285

Text #5

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0385. Min Act: -0.0002

Data Index: 3080 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0382. Min Act: -0.0002

Data Index: 108474 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0364. Min Act: -0.0002

Data Index: 602659 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0363. Min Act: -0.0003

Data Index: 303442 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0362. Min Act: -0.0003

Data Index: 950491 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1648105 (Python Code)

Max Activating Token Index: 826

Text #11

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0354. Min Act: -0.0002

Data Index: 131451 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0363. Min Act: -0.0003

Data Index: 46156 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1436064 (Python Code)

Max Activating Token Index: 794

Text #14

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0343. Min Act: -0.0003

Data Index: 658208 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0344. Min Act: -0.0003

Data Index: 418105 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0339. Min Act: -0.0002

Data Index: 116456 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1116254 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0326. Min Act: -0.0003

Data Index: 102003 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1464746 (Python Code)

Max Activating Token Index: 262