Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1804 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0637. Min Range: -1.0637

Max Act: 1.0637. Min Act: -0.0000

Data Index: 1484656 (Python Code)

Max Activating Token Index: 923

Text #1

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9130. Min Act: -0.0000

Data Index: 37537 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1592173 (Python Code)

Max Activating Token Index: 905

Text #3

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1332925 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1531055 (Python Code)

Max Activating Token Index: 651

Text #5

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1575667 (Python Code)

Max Activating Token Index: 957

Text #6

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1655308 (Python Code)

Max Activating Token Index: 428

Text #7

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1516913 (Python Code)

Max Activating Token Index: 736

Text #8

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1272597 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1334198 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1392807 (Python Code)

Max Activating Token Index: 275

Text #11

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.7868. Min Act: -0.0000

Data Index: 377624 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1407746 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1608392 (Python Code)

Max Activating Token Index: 869

Text #14

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.7581. Min Act: -0.0000

Data Index: 1616236 (Python Code)

Max Activating Token Index: 646

Text #15

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1491828 (Python Code)

Max Activating Token Index: 435

Text #16

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1564427 (Python Code)

Max Activating Token Index: 416

Text #17

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1573834 (Python Code)

Max Activating Token Index: 3

Text #18

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.7470. Min Act: -0.0000

Data Index: 1321280 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1560759 (Python Code)

Max Activating Token Index: 532