Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2362 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1293155 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0364. Min Act: -0.0001

Data Index: 974463 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0370. Min Act: -0.0001

Data Index: 904211 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0391. Min Act: -0.0001

Data Index: 334393 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1245225 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1509663 (Python Code)

Max Activating Token Index: 102

Text #6

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0333. Min Act: -0.0001

Data Index: 549739 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0384. Min Act: -0.0001

Data Index: 379301 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0388. Min Act: -0.0001

Data Index: 801695 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0397. Min Act: -0.0001

Data Index: 714357 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0374. Min Act: -0.0001

Data Index: 927248 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1366988 (Python Code)

Max Activating Token Index: 965

Text #12

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0325. Min Act: -0.0001

Data Index: 774325 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1473475 (Python Code)

Max Activating Token Index: 84

Text #14

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0318. Min Act: -0.0001

Data Index: 59065 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0301. Min Act: -0.0001

Data Index: 759728 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1622336 (Python Code)

Max Activating Token Index: 968

Text #17

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1336615 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0327. Min Act: -0.0001

Data Index: 153207 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1309225 (C4 (Web Text))

Max Activating Token Index: 297