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

Dataset: The Pile

Neuron 97 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4157. Min Range: -1.4157

Max Act: 1.4157. Min Act: -0.0000

Data Index: 1763920 (The Pile)

Max Activating Token Index: 856

Text #1

Max Range: 1.4157. Min Range: -1.4157

Max Act: 1.3344. Min Act: -0.0000

Data Index: 1397218 (The Pile)

Max Activating Token Index: 308

Text #2

Max Range: 1.4157. Min Range: -1.4157

Max Act: 1.2750. Min Act: -0.0000

Data Index: 280097 (The Pile)

Max Activating Token Index: 816

Text #3

Max Range: 1.4157. Min Range: -1.4157

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1358708 (The Pile)

Max Activating Token Index: 882

Text #4

Max Range: 1.4157. Min Range: -1.4157

Max Act: 1.1447. Min Act: -0.0000

Data Index: 1444721 (The Pile)

Max Activating Token Index: 367

Text #5

Max Range: 1.4157. Min Range: -1.4157

Max Act: 1.1988. Min Act: -0.0000

Data Index: 273999 (The Pile)

Max Activating Token Index: 203

Text #6

Max Range: 1.4157. Min Range: -1.4157

Max Act: 1.0805. Min Act: -0.0000

Data Index: 232105 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 1.4157. Min Range: -1.4157

Max Act: 1.0515. Min Act: -0.0000

Data Index: 1300273 (The Pile)

Max Activating Token Index: 340

Text #8

Max Range: 1.4157. Min Range: -1.4157

Max Act: 1.1437. Min Act: -0.0000

Data Index: 584500 (The Pile)

Max Activating Token Index: 596

Text #9

Max Range: 1.4157. Min Range: -1.4157

Max Act: 1.0720. Min Act: -0.0000

Data Index: 567533 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 1.4157. Min Range: -1.4157

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1910220 (The Pile)

Max Activating Token Index: 778

Text #11

Max Range: 1.4157. Min Range: -1.4157

Max Act: 0.9448. Min Act: -0.0000

Data Index: 215544 (The Pile)

Max Activating Token Index: 942

Text #12

Max Range: 1.4157. Min Range: -1.4157

Max Act: 0.9890. Min Act: -0.0000

Data Index: 150625 (The Pile)

Max Activating Token Index: 822

Text #13

Max Range: 1.4157. Min Range: -1.4157

Max Act: 0.8477. Min Act: -0.0000

Data Index: 697492 (The Pile)

Max Activating Token Index: 161

Text #14

Max Range: 1.4157. Min Range: -1.4157

Max Act: 0.9500. Min Act: -0.0000

Data Index: 470072 (The Pile)

Max Activating Token Index: 678

Text #15

Max Range: 1.4157. Min Range: -1.4157

Max Act: 1.0342. Min Act: -0.0000

Data Index: 802990 (The Pile)

Max Activating Token Index: 1008

Text #16

Max Range: 1.4157. Min Range: -1.4157

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1595896 (The Pile)

Max Activating Token Index: 895

Text #17

Max Range: 1.4157. Min Range: -1.4157

Max Act: 1.0207. Min Act: -0.0000

Data Index: 1730974 (The Pile)

Max Activating Token Index: 621

Text #18

Max Range: 1.4157. Min Range: -1.4157

Max Act: 1.0299. Min Act: -0.0000

Data Index: 246593 (The Pile)

Max Activating Token Index: 294

Text #19

Max Range: 1.4157. Min Range: -1.4157

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1309586 (The Pile)

Max Activating Token Index: 490