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

Dataset: The Pile

Neuron 811 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.6075. Min Act: -0.0000

Data Index: 774123 (The Pile)

Max Activating Token Index: 375

Text #1

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.5174. Min Act: -0.0000

Data Index: 118056 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1808085 (The Pile)

Max Activating Token Index: 387

Text #3

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1066098 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.5368. Min Act: -0.0000

Data Index: 296327 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.5126. Min Act: -0.0000

Data Index: 1717907 (The Pile)

Max Activating Token Index: 914

Text #6

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1226693 (The Pile)

Max Activating Token Index: 676

Text #7

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4210. Min Act: -0.0000

Data Index: 716703 (The Pile)

Max Activating Token Index: 194

Text #8

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4476. Min Act: -0.0000

Data Index: 359223 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4658. Min Act: -0.0000

Data Index: 381580 (The Pile)

Max Activating Token Index: 578

Text #10

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.5031. Min Act: -0.0000

Data Index: 713745 (The Pile)

Max Activating Token Index: 297

Text #11

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4229. Min Act: -0.0000

Data Index: 677546 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4418. Min Act: -0.0000

Data Index: 553013 (The Pile)

Max Activating Token Index: 114

Text #13

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1798447 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1814778 (The Pile)

Max Activating Token Index: 1004

Text #15

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1332998 (The Pile)

Max Activating Token Index: 578

Text #16

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4065. Min Act: -0.0000

Data Index: 940775 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1794757 (The Pile)

Max Activating Token Index: 770

Text #18

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1152856 (The Pile)

Max Activating Token Index: 646

Text #19

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1273942 (The Pile)

Max Activating Token Index: 369