Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2202 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.8250. Min Act: -0.0000

Data Index: 304997 (The Pile)

Max Activating Token Index: 857

Text #1

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7383. Min Act: -0.0000

Data Index: 1975841 (The Pile)

Max Activating Token Index: 207

Text #2

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1670396 (The Pile)

Max Activating Token Index: 514

Text #3

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1559228 (The Pile)

Max Activating Token Index: 343

Text #4

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1816681 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7587. Min Act: 0.0000

Data Index: 370454 (The Pile)

Max Activating Token Index: 729

Text #6

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1921614 (The Pile)

Max Activating Token Index: 478

Text #7

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1859508 (The Pile)

Max Activating Token Index: 476

Text #8

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6662. Min Act: 0.0001

Data Index: 1421855 (The Pile)

Max Activating Token Index: 334

Text #9

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1080238 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6767. Min Act: 0.0000

Data Index: 1863451 (The Pile)

Max Activating Token Index: 745

Text #11

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6215. Min Act: -0.0000

Data Index: 528445 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1207834 (The Pile)

Max Activating Token Index: 742

Text #13

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6412. Min Act: 0.0000

Data Index: 1559630 (The Pile)

Max Activating Token Index: 1009

Text #14

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1331802 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6318. Min Act: -0.0000

Data Index: 147600 (The Pile)

Max Activating Token Index: 929

Text #16

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6051. Min Act: -0.0000

Data Index: 585131 (The Pile)

Max Activating Token Index: 834

Text #17

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1273228 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6058. Min Act: -0.0000

Data Index: 631812 (The Pile)

Max Activating Token Index: 546

Text #19

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.5428. Min Act: -0.0000

Data Index: 385406 (The Pile)

Max Activating Token Index: 290