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

Dataset: The Pile

Neuron 4737 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.3338. Min Act: -0.0000

Data Index: 654195 (The Pile)

Max Activating Token Index: 854

Text #1

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.0106. Min Act: -0.0000

Data Index: 226722 (The Pile)

Max Activating Token Index: 328

Text #2

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1581133 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.9664. Min Act: -0.0000

Data Index: 1607597 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.9500. Min Act: -0.0000

Data Index: 839861 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 1.3338. Min Range: -1.3338

Max Act: 1.1004. Min Act: -0.0001

Data Index: 1988878 (The Pile)

Max Activating Token Index: 786

Text #6

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.9556. Min Act: -0.0000

Data Index: 1757059 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.8593. Min Act: -0.0000

Data Index: 827055 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.7909. Min Act: -0.0000

Data Index: 463247 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1961176 (The Pile)

Max Activating Token Index: 341

Text #10

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.8244. Min Act: -0.0000

Data Index: 839554 (The Pile)

Max Activating Token Index: 837

Text #11

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.7523. Min Act: -0.0000

Data Index: 485191 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1382143 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.8367. Min Act: -0.0000

Data Index: 943093 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1705524 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.8088. Min Act: -0.0000

Data Index: 216208 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1823780 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.8165. Min Act: -0.0000

Data Index: 271039 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1237137 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 1.3338. Min Range: -1.3338

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1765084 (The Pile)

Max Activating Token Index: 916