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

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

Neuron 525 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: 0.0477. Min Range: -0.0477

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1003174 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1407409 (Python Code)

Max Activating Token Index: 942

Text #2

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1206147 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0353. Min Act: -0.0002

Data Index: 743848 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1272328 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0346. Min Act: -0.0002

Data Index: 398712 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1560654 (Python Code)

Max Activating Token Index: 455

Text #7

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1352986 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0343. Min Act: -0.0002

Data Index: 339984 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1154235 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0341. Min Act: -0.0002

Data Index: 674746 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0338. Min Act: -0.0002

Data Index: 987754 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0326. Min Act: -0.0002

Data Index: 600632 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0326. Min Act: -0.0002

Data Index: 965740 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1212286 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1246789 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1471396 (Python Code)

Max Activating Token Index: 578

Text #17

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0313. Min Act: -0.0003

Data Index: 328474 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1013561 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1254647 (C4 (Web Text))

Max Activating Token Index: 306