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

Dataset: The Pile

Neuron 1057 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: 5.1152. Min Range: -5.1152

Max Act: 4.8530. Min Act: -0.0000

Data Index: 1542364 (The Pile)

Max Activating Token Index: 612

Text #1

Max Range: 5.1152. Min Range: -5.1152

Max Act: 5.1152. Min Act: -0.0000

Data Index: 1038423 (The Pile)

Max Activating Token Index: 920

Text #2

Max Range: 5.1152. Min Range: -5.1152

Max Act: 4.6093. Min Act: -0.0000

Data Index: 311607 (The Pile)

Max Activating Token Index: 262

Text #3

Max Range: 5.1152. Min Range: -5.1152

Max Act: 4.2044. Min Act: -0.0000

Data Index: 355599 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 5.1152. Min Range: -5.1152

Max Act: 3.6771. Min Act: -0.0000

Data Index: 1779571 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 5.1152. Min Range: -5.1152

Max Act: 3.9283. Min Act: -0.0000

Data Index: 97939 (The Pile)

Max Activating Token Index: 746

Text #6

Max Range: 5.1152. Min Range: -5.1152

Max Act: 3.7074. Min Act: -0.0000

Data Index: 648545 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 5.1152. Min Range: -5.1152

Max Act: 3.2023. Min Act: -0.0000

Data Index: 950848 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 5.1152. Min Range: -5.1152

Max Act: 3.3844. Min Act: -0.0000

Data Index: 474894 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 5.1152. Min Range: -5.1152

Max Act: 3.9218. Min Act: -0.0000

Data Index: 1340862 (The Pile)

Max Activating Token Index: 615

Text #10

Max Range: 5.1152. Min Range: -5.1152

Max Act: 3.5065. Min Act: -0.0000

Data Index: 913011 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 5.1152. Min Range: -5.1152

Max Act: 3.4054. Min Act: -0.0000

Data Index: 884719 (The Pile)

Max Activating Token Index: 639

Text #12

Max Range: 5.1152. Min Range: -5.1152

Max Act: 3.2157. Min Act: -0.0000

Data Index: 668048 (The Pile)

Max Activating Token Index: 67

Text #13

Max Range: 5.1152. Min Range: -5.1152

Max Act: 3.3811. Min Act: -0.0000

Data Index: 852454 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 5.1152. Min Range: -5.1152

Max Act: 2.9296. Min Act: -0.0000

Data Index: 39254 (The Pile)

Max Activating Token Index: 919

Text #15

Max Range: 5.1152. Min Range: -5.1152

Max Act: 3.4123. Min Act: -0.0000

Data Index: 372565 (The Pile)

Max Activating Token Index: 717

Text #16

Max Range: 5.1152. Min Range: -5.1152

Max Act: 3.4555. Min Act: -0.0000

Data Index: 81391 (The Pile)

Max Activating Token Index: 89

Text #17

Max Range: 5.1152. Min Range: -5.1152

Max Act: 3.2138. Min Act: -0.0000

Data Index: 745834 (The Pile)

Max Activating Token Index: 521

Text #18

Max Range: 5.1152. Min Range: -5.1152

Max Act: 2.8234. Min Act: -0.0000

Data Index: 649353 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 5.1152. Min Range: -5.1152

Max Act: 2.7116. Min Act: -0.0000

Data Index: 1085791 (The Pile)

Max Activating Token Index: 82