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

Dataset: The Pile

Neuron 1263 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0346. Min Range: -1.0346

Max Act: 1.0255. Min Act: -0.0000

Data Index: 1396922 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 1.0346. Min Range: -1.0346

Max Act: 1.0346. Min Act: -0.0000

Data Index: 930266 (The Pile)

Max Activating Token Index: 184

Text #2

Max Range: 1.0346. Min Range: -1.0346

Max Act: 1.0174. Min Act: -0.0000

Data Index: 1986476 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1733823 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1366428 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1212610 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9004. Min Act: -0.0000

Data Index: 478552 (The Pile)

Max Activating Token Index: 223

Text #7

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1781257 (The Pile)

Max Activating Token Index: 312

Text #8

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8357. Min Act: -0.0000

Data Index: 52366 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7983. Min Act: -0.0000

Data Index: 853496 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8138. Min Act: -0.0000

Data Index: 545979 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7899. Min Act: -0.0000

Data Index: 687526 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8127. Min Act: -0.0000

Data Index: 918857 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8521. Min Act: -0.0000

Data Index: 560438 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7807. Min Act: -0.0000

Data Index: 559942 (The Pile)

Max Activating Token Index: 674

Text #15

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1516958 (The Pile)

Max Activating Token Index: 941

Text #16

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8438. Min Act: -0.0000

Data Index: 450832 (The Pile)

Max Activating Token Index: 886

Text #17

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1802570 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8249. Min Act: -0.0000

Data Index: 621768 (The Pile)

Max Activating Token Index: 368

Text #19

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1567712 (The Pile)

Max Activating Token Index: 152