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

Dataset: The Pile

Neuron 15 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: 1.2284. Min Range: -1.2284

Max Act: 1.2183. Min Act: -0.0000

Data Index: 263715 (The Pile)

Max Activating Token Index: 215

Text #1

Max Range: 1.2284. Min Range: -1.2284

Max Act: 1.2284. Min Act: -0.0000

Data Index: 805198 (The Pile)

Max Activating Token Index: 372

Text #2

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1013375 (The Pile)

Max Activating Token Index: 675

Text #3

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1939623 (The Pile)

Max Activating Token Index: 444

Text #4

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9647. Min Act: -0.0000

Data Index: 1716401 (The Pile)

Max Activating Token Index: 499

Text #5

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1776185 (The Pile)

Max Activating Token Index: 222

Text #6

Max Range: 1.2284. Min Range: -1.2284

Max Act: 1.0615. Min Act: -0.0000

Data Index: 411568 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1736030 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.8806. Min Act: -0.0000

Data Index: 1679355 (The Pile)

Max Activating Token Index: 384

Text #9

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1990190 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9975. Min Act: -0.0000

Data Index: 399134 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1575899 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.8957. Min Act: -0.0000

Data Index: 479647 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9302. Min Act: -0.0000

Data Index: 215768 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1687522 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9424. Min Act: -0.0000

Data Index: 391520 (The Pile)

Max Activating Token Index: 487

Text #16

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9113. Min Act: -0.0000

Data Index: 670411 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1697460 (The Pile)

Max Activating Token Index: 983

Text #18

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9015. Min Act: -0.0000

Data Index: 537045 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1747983 (The Pile)

Max Activating Token Index: 870