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

Dataset: The Pile

Neuron 2194 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3748. Min Range: -3.3748

Max Act: 3.2838. Min Act: -0.0000

Data Index: 1456058 (The Pile)

Max Activating Token Index: 84

Text #1

Max Range: 3.3748. Min Range: -3.3748

Max Act: 3.3536. Min Act: -0.0000

Data Index: 1941610 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 3.3748. Min Range: -3.3748

Max Act: 3.3029. Min Act: -0.0000

Data Index: 1456486 (The Pile)

Max Activating Token Index: 374

Text #3

Max Range: 3.3748. Min Range: -3.3748

Max Act: 3.2739. Min Act: -0.0000

Data Index: 1407236 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 3.3748. Min Range: -3.3748

Max Act: 3.1088. Min Act: -0.0000

Data Index: 1699506 (The Pile)

Max Activating Token Index: 262

Text #5

Max Range: 3.3748. Min Range: -3.3748

Max Act: 3.2448. Min Act: -0.0000

Data Index: 1830002 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 3.3748. Min Range: -3.3748

Max Act: 3.3748. Min Act: -0.0000

Data Index: 132076 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 3.3748. Min Range: -3.3748

Max Act: 3.1418. Min Act: -0.0000

Data Index: 150169 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 3.3748. Min Range: -3.3748

Max Act: 2.9794. Min Act: -0.0000

Data Index: 1880730 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 3.3748. Min Range: -3.3748

Max Act: 3.1104. Min Act: -0.0000

Data Index: 192910 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 3.3748. Min Range: -3.3748

Max Act: 3.1194. Min Act: -0.0000

Data Index: 52506 (The Pile)

Max Activating Token Index: 836

Text #11

Max Range: 3.3748. Min Range: -3.3748

Max Act: 2.9341. Min Act: -0.0000

Data Index: 1674569 (The Pile)

Max Activating Token Index: 721

Text #12

Max Range: 3.3748. Min Range: -3.3748

Max Act: 2.7703. Min Act: -0.0000

Data Index: 1852826 (The Pile)

Max Activating Token Index: 848

Text #13

Max Range: 3.3748. Min Range: -3.3748

Max Act: 2.9052. Min Act: -0.0000

Data Index: 734204 (The Pile)

Max Activating Token Index: 920

Text #14

Max Range: 3.3748. Min Range: -3.3748

Max Act: 2.8991. Min Act: -0.0000

Data Index: 784148 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 3.3748. Min Range: -3.3748

Max Act: 2.8540. Min Act: -0.0000

Data Index: 636201 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 3.3748. Min Range: -3.3748

Max Act: 2.6868. Min Act: -0.0000

Data Index: 1329219 (The Pile)

Max Activating Token Index: 421

Text #17

Max Range: 3.3748. Min Range: -3.3748

Max Act: 2.8095. Min Act: -0.0000

Data Index: 924054 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 3.3748. Min Range: -3.3748

Max Act: 2.9303. Min Act: -0.0000

Data Index: 1264593 (The Pile)

Max Activating Token Index: 505

Text #19

Max Range: 3.3748. Min Range: -3.3748

Max Act: 2.9163. Min Act: -0.0000

Data Index: 1116995 (The Pile)

Max Activating Token Index: 108