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

Dataset: The Pile

Neuron 2749 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: 1.2391. Min Range: -1.2391

Max Act: 1.1850. Min Act: -0.0000

Data Index: 658628 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 1.2391. Min Range: -1.2391

Max Act: 1.2391. Min Act: -0.0000

Data Index: 1240560 (The Pile)

Max Activating Token Index: 770

Text #2

Max Range: 1.2391. Min Range: -1.2391

Max Act: 1.1034. Min Act: -0.0000

Data Index: 1470205 (The Pile)

Max Activating Token Index: 691

Text #3

Max Range: 1.2391. Min Range: -1.2391

Max Act: 1.0545. Min Act: -0.0000

Data Index: 399490 (The Pile)

Max Activating Token Index: 232

Text #4

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1468573 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9883. Min Act: -0.0000

Data Index: 1380058 (The Pile)

Max Activating Token Index: 353

Text #6

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9695. Min Act: -0.0000

Data Index: 240800 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1724769 (The Pile)

Max Activating Token Index: 184

Text #8

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9757. Min Act: -0.0000

Data Index: 185064 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9387. Min Act: -0.0000

Data Index: 429416 (The Pile)

Max Activating Token Index: 214

Text #10

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9038. Min Act: -0.0000

Data Index: 196643 (The Pile)

Max Activating Token Index: 152

Text #11

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9240. Min Act: -0.0000

Data Index: 912260 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1075543 (The Pile)

Max Activating Token Index: 795

Text #13

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1279049 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1691030 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1771822 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8464. Min Act: -0.0000

Data Index: 316784 (The Pile)

Max Activating Token Index: 385

Text #17

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8393. Min Act: -0.0000

Data Index: 653777 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8672. Min Act: -0.0000

Data Index: 240606 (The Pile)

Max Activating Token Index: 862

Text #19

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1592491 (The Pile)

Max Activating Token Index: 937