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

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

Neuron 1884 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1478065 (Python Code)

Max Activating Token Index: 880

Text #1

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1479107 (Python Code)

Max Activating Token Index: 967

Text #2

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1580545 (Python Code)

Max Activating Token Index: 438

Text #3

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1576956 (Python Code)

Max Activating Token Index: 819

Text #4

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1476242 (Python Code)

Max Activating Token Index: 425

Text #5

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1581534 (Python Code)

Max Activating Token Index: 600

Text #6

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1508990 (Python Code)

Max Activating Token Index: 447

Text #7

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1597548 (Python Code)

Max Activating Token Index: 473

Text #8

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1500859 (Python Code)

Max Activating Token Index: 685

Text #9

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1320503 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1417556 (Python Code)

Max Activating Token Index: 568

Text #11

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1375656 (Python Code)

Max Activating Token Index: 777

Text #12

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1368146 (Python Code)

Max Activating Token Index: 361

Text #13

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1065816 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1504911 (Python Code)

Max Activating Token Index: 745

Text #15

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0339. Min Act: -0.0002

Data Index: 191682 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1615012 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1311715 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1486618 (Python Code)

Max Activating Token Index: 909

Text #19

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1655528 (Python Code)

Max Activating Token Index: 766