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

Dataset: The Pile

Neuron 3644 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.1439. Min Act: -0.0000

Data Index: 1651792 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.4607. Min Act: -0.0000

Data Index: 1888153 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.6637. Min Act: -0.0000

Data Index: 130195 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.4376. Min Act: -0.0000

Data Index: 1979982 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.4695. Min Act: -0.0000

Data Index: 1851328 (The Pile)

Max Activating Token Index: 75

Text #5

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.4169. Min Act: -0.0000

Data Index: 1924038 (The Pile)

Max Activating Token Index: 910

Text #6

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.1826. Min Act: -0.0000

Data Index: 1223022 (The Pile)

Max Activating Token Index: 195

Text #7

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.1216. Min Act: -0.0000

Data Index: 1679032 (The Pile)

Max Activating Token Index: 211

Text #8

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.9900. Min Act: 0.0000

Data Index: 63400 (The Pile)

Max Activating Token Index: 661

Text #9

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.8968. Min Act: -0.0000

Data Index: 606542 (The Pile)

Max Activating Token Index: 371

Text #10

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.1070. Min Act: -0.0000

Data Index: 163837 (The Pile)

Max Activating Token Index: 564

Text #11

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.9709. Min Act: -0.0000

Data Index: 107250 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.8539. Min Act: -0.0000

Data Index: 617276 (The Pile)

Max Activating Token Index: 35

Text #13

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.9194. Min Act: -0.0000

Data Index: 853643 (The Pile)

Max Activating Token Index: 405

Text #14

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.9415. Min Act: -0.0000

Data Index: 1091721 (The Pile)

Max Activating Token Index: 467

Text #15

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.0203. Min Act: 0.0000

Data Index: 1311381 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.8662. Min Act: -0.0000

Data Index: 1356096 (The Pile)

Max Activating Token Index: 658

Text #17

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.9358. Min Act: -0.0000

Data Index: 835884 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.8267. Min Act: -0.0000

Data Index: 1150123 (The Pile)

Max Activating Token Index: 961

Text #19

Max Range: 3.1439. Min Range: -3.1439

Max Act: 1.9100. Min Act: -0.0000

Data Index: 310473 (The Pile)

Max Activating Token Index: 970