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

Dataset: The Pile

Neuron 4257 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0354. Min Act: 0.0000

Data Index: 1774094 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1828354 (The Pile)

Max Activating Token Index: 10

Text #2

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0342. Min Act: -0.0000

Data Index: 1699876 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0339. Min Act: 0.0000

Data Index: 739139 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0349. Min Act: -0.0000

Data Index: 799195 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0336. Min Act: -0.0000

Data Index: 472316 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0333. Min Act: 0.0000

Data Index: 625054 (The Pile)

Max Activating Token Index: 14

Text #7

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0330. Min Act: 0.0000

Data Index: 1561534 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0329. Min Act: 0.0000

Data Index: 1368718 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1017195 (The Pile)

Max Activating Token Index: 14

Text #10

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0326. Min Act: 0.0000

Data Index: 639410 (The Pile)

Max Activating Token Index: 10

Text #11

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0326. Min Act: 0.0000

Data Index: 20783 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0326. Min Act: 0.0000

Data Index: 711031 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0336. Min Act: 0.0000

Data Index: 1051812 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0323. Min Act: -0.0000

Data Index: 834989 (The Pile)

Max Activating Token Index: 10

Text #15

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0323. Min Act: 0.0000

Data Index: 774980 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0324. Min Act: 0.0000

Data Index: 1944107 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0322. Min Act: -0.0000

Data Index: 790089 (The Pile)

Max Activating Token Index: 12

Text #18

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0321. Min Act: 0.0000

Data Index: 1311716 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0321. Min Act: 0.0000

Data Index: 1855416 (The Pile)

Max Activating Token Index: 14