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

Dataset: The Pile

Neuron 3581 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.8900. Min Act: -0.0000

Data Index: 1157248 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.5663. Min Act: -0.0000

Data Index: 1202171 (The Pile)

Max Activating Token Index: 766

Text #2

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.4247. Min Act: -0.0000

Data Index: 1774715 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.4050. Min Act: -0.0000

Data Index: 5897 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.3107. Min Act: -0.0000

Data Index: 1615438 (The Pile)

Max Activating Token Index: 262

Text #5

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.3825. Min Act: -0.0000

Data Index: 1849049 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.3033. Min Act: 0.0000

Data Index: 996357 (The Pile)

Max Activating Token Index: 967

Text #7

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1024947 (The Pile)

Max Activating Token Index: 482

Text #8

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.2408. Min Act: -0.0000

Data Index: 275294 (The Pile)

Max Activating Token Index: 872

Text #9

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.2103. Min Act: -0.0000

Data Index: 1829844 (The Pile)

Max Activating Token Index: 563

Text #10

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1648242 (The Pile)

Max Activating Token Index: 541

Text #11

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.1357. Min Act: -0.0000

Data Index: 1145535 (The Pile)

Max Activating Token Index: 694

Text #12

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.1136. Min Act: -0.0000

Data Index: 348781 (The Pile)

Max Activating Token Index: 370

Text #13

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1743086 (The Pile)

Max Activating Token Index: 242

Text #14

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.1988. Min Act: -0.0000

Data Index: 1425829 (The Pile)

Max Activating Token Index: 229

Text #15

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.1149. Min Act: -0.0000

Data Index: 1563829 (The Pile)

Max Activating Token Index: 895

Text #16

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.0476. Min Act: -0.0000

Data Index: 1662055 (The Pile)

Max Activating Token Index: 261

Text #17

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.0916. Min Act: -0.0000

Data Index: 1603917 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.0199. Min Act: -0.0000

Data Index: 297464 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.0395. Min Act: -0.0000

Data Index: 417390 (The Pile)

Max Activating Token Index: 103