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

Dataset: The Pile

Neuron 3894 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.7233. Min Act: -0.0000

Data Index: 1818768 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.2984. Min Act: -0.0000

Data Index: 935341 (The Pile)

Max Activating Token Index: 564

Text #2

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.3362. Min Act: -0.0000

Data Index: 512578 (The Pile)

Max Activating Token Index: 302

Text #3

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.1617. Min Act: -0.0000

Data Index: 155471 (The Pile)

Max Activating Token Index: 728

Text #4

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.1225. Min Act: -0.0000

Data Index: 1905325 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1618976 (The Pile)

Max Activating Token Index: 325

Text #6

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.1272. Min Act: -0.0000

Data Index: 1591922 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.1680. Min Act: -0.0000

Data Index: 333044 (The Pile)

Max Activating Token Index: 786

Text #8

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.2116. Min Act: -0.0000

Data Index: 361301 (The Pile)

Max Activating Token Index: 169

Text #9

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.0432. Min Act: -0.0000

Data Index: 1122396 (The Pile)

Max Activating Token Index: 117

Text #10

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.1351. Min Act: -0.0000

Data Index: 1034057 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1112369 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1092159 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.0283. Min Act: -0.0000

Data Index: 773601 (The Pile)

Max Activating Token Index: 90

Text #14

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.0251. Min Act: -0.0000

Data Index: 654361 (The Pile)

Max Activating Token Index: 236

Text #15

Max Range: 1.7233. Min Range: -1.7233

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1231295 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.0097. Min Act: -0.0000

Data Index: 1207881 (The Pile)

Max Activating Token Index: 441

Text #17

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1435488 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 1.7233. Min Range: -1.7233

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1148324 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 1.7233. Min Range: -1.7233

Max Act: 0.8616. Min Act: -0.0000

Data Index: 70322 (The Pile)

Max Activating Token Index: 757