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

Dataset: The Pile

Neuron 3360 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: 0.7203. Min Range: -0.7203

Max Act: 0.7203. Min Act: -0.0000

Data Index: 371718 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1119557 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6642. Min Act: -0.0000

Data Index: 753665 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1249933 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6363. Min Act: -0.0000

Data Index: 780947 (The Pile)

Max Activating Token Index: 953

Text #5

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1248917 (The Pile)

Max Activating Token Index: 370

Text #6

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6379. Min Act: -0.0000

Data Index: 999130 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1213958 (The Pile)

Max Activating Token Index: 106

Text #8

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1351742 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5611. Min Act: 0.0000

Data Index: 1053946 (The Pile)

Max Activating Token Index: 208

Text #10

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5893. Min Act: -0.0000

Data Index: 296432 (The Pile)

Max Activating Token Index: 861

Text #11

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1956152 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1692258 (The Pile)

Max Activating Token Index: 728

Text #13

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5355. Min Act: -0.0000

Data Index: 772905 (The Pile)

Max Activating Token Index: 674

Text #14

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5291. Min Act: 0.0000

Data Index: 1839521 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1117031 (The Pile)

Max Activating Token Index: 964

Text #16

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1120337 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1448689 (The Pile)

Max Activating Token Index: 590

Text #18

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1096794 (The Pile)

Max Activating Token Index: 440

Text #19

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1812349 (The Pile)

Max Activating Token Index: 647