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

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

Neuron 4663 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1620880 (Python Code)

Max Activating Token Index: 191

Text #1

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1605401 (Python Code)

Max Activating Token Index: 198

Text #2

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1532032 (Python Code)

Max Activating Token Index: 229

Text #3

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1548390 (Python Code)

Max Activating Token Index: 278

Text #4

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1545356 (Python Code)

Max Activating Token Index: 132

Text #5

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1544561 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1568863 (Python Code)

Max Activating Token Index: 145

Text #7

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1528514 (Python Code)

Max Activating Token Index: 71

Text #8

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1518233 (Python Code)

Max Activating Token Index: 154

Text #9

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1447247 (Python Code)

Max Activating Token Index: 407

Text #10

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1419221 (Python Code)

Max Activating Token Index: 395

Text #11

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1630477 (Python Code)

Max Activating Token Index: 333

Text #12

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1494049 (Python Code)

Max Activating Token Index: 287

Text #13

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2500. Min Act: -0.0000

Data Index: 613647 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1423362 (Python Code)

Max Activating Token Index: 536

Text #15

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2389. Min Act: -0.0000

Data Index: 682668 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1447136 (Python Code)

Max Activating Token Index: 590

Text #17

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1626730 (Python Code)

Max Activating Token Index: 533

Text #18

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2272. Min Act: -0.0000

Data Index: 363551 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1410856 (Python Code)

Max Activating Token Index: 986