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

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

Neuron 92 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.7637. Min Act: -0.0001

Data Index: 1405475 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.3686. Min Act: -0.0001

Data Index: 1639694 (Python Code)

Max Activating Token Index: 705

Text #2

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.3190. Min Act: -0.0001

Data Index: 1544752 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.2282. Min Act: -0.0001

Data Index: 1385042 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.2584. Min Act: -0.0001

Data Index: 1645515 (Python Code)

Max Activating Token Index: 29

Text #5

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.2624. Min Act: -0.0001

Data Index: 1443305 (Python Code)

Max Activating Token Index: 150

Text #6

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.1564. Min Act: -0.0001

Data Index: 1382240 (Python Code)

Max Activating Token Index: 395

Text #7

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.1989. Min Act: -0.0001

Data Index: 1576248 (Python Code)

Max Activating Token Index: 80

Text #8

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.2228. Min Act: -0.0001

Data Index: 1411999 (Python Code)

Max Activating Token Index: 173

Text #9

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.1881. Min Act: -0.0001

Data Index: 1631674 (Python Code)

Max Activating Token Index: 207

Text #10

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.1418. Min Act: -0.0002

Data Index: 1452330 (Python Code)

Max Activating Token Index: 85

Text #11

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.1406. Min Act: -0.0002

Data Index: 1478867 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.1698. Min Act: -0.0001

Data Index: 1474091 (Python Code)

Max Activating Token Index: 618

Text #13

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.1605. Min Act: -0.0001

Data Index: 1580759 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.1347. Min Act: -0.0001

Data Index: 1497912 (Python Code)

Max Activating Token Index: 874

Text #15

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.1878. Min Act: -0.0001

Data Index: 1581431 (Python Code)

Max Activating Token Index: 862

Text #16

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.2178. Min Act: -0.0001

Data Index: 1557476 (Python Code)

Max Activating Token Index: 664

Text #17

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.1423. Min Act: -0.0001

Data Index: 1496123 (Python Code)

Max Activating Token Index: 212

Text #18

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.2559. Min Act: -0.0001

Data Index: 1630734 (Python Code)

Max Activating Token Index: 61

Text #19

Max Range: 1.7637. Min Range: -1.7637

Max Act: 1.1898. Min Act: -0.0001

Data Index: 1580083 (Python Code)

Max Activating Token Index: 592