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

Dataset: The Pile

Neuron 1604 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.3045. Min Act: -0.0000

Data Index: 816456 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.2127. Min Act: -0.0000

Data Index: 1161994 (The Pile)

Max Activating Token Index: 499

Text #2

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.1726. Min Act: -0.0000

Data Index: 310770 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1148738 (The Pile)

Max Activating Token Index: 614

Text #4

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.1267. Min Act: -0.0000

Data Index: 816187 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.0430. Min Act: -0.0000

Data Index: 292823 (The Pile)

Max Activating Token Index: 844

Text #6

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1608100 (The Pile)

Max Activating Token Index: 484

Text #7

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.0122. Min Act: -0.0000

Data Index: 818275 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.0018. Min Act: -0.0000

Data Index: 943209 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1023935 (The Pile)

Max Activating Token Index: 120

Text #10

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.0402. Min Act: -0.0000

Data Index: 1327726 (The Pile)

Max Activating Token Index: 537

Text #11

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.0364. Min Act: -0.0000

Data Index: 363683 (The Pile)

Max Activating Token Index: 349

Text #12

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9611. Min Act: -0.0000

Data Index: 479225 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.8840. Min Act: -0.0000

Data Index: 72796 (The Pile)

Max Activating Token Index: 725

Text #14

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9281. Min Act: -0.0000

Data Index: 1943234 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9369. Min Act: -0.0000

Data Index: 550255 (The Pile)

Max Activating Token Index: 193

Text #16

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9506. Min Act: -0.0000

Data Index: 221541 (The Pile)

Max Activating Token Index: 233

Text #17

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9660. Min Act: -0.0000

Data Index: 219240 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9051. Min Act: -0.0000

Data Index: 22277 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9016. Min Act: -0.0000

Data Index: 861519 (The Pile)

Max Activating Token Index: 303