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

Dataset: The Pile

Neuron 2950 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.8320. Min Act: -0.0001

Data Index: 288621 (The Pile)

Max Activating Token Index: 966

Text #1

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.4311. Min Act: -0.0001

Data Index: 1268206 (The Pile)

Max Activating Token Index: 427

Text #2

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.5005. Min Act: -0.0001

Data Index: 81130 (The Pile)

Max Activating Token Index: 921

Text #3

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.1174. Min Act: -0.0001

Data Index: 53729 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.2798. Min Act: -0.0001

Data Index: 1852233 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.0986. Min Act: -0.0001

Data Index: 334902 (The Pile)

Max Activating Token Index: 515

Text #6

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.1722. Min Act: -0.0001

Data Index: 1729160 (The Pile)

Max Activating Token Index: 392

Text #7

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.2740. Min Act: -0.0001

Data Index: 1033648 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.2263. Min Act: -0.0001

Data Index: 143247 (The Pile)

Max Activating Token Index: 47

Text #9

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.2538. Min Act: -0.0001

Data Index: 1529332 (The Pile)

Max Activating Token Index: 623

Text #10

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.0990. Min Act: -0.0001

Data Index: 1580116 (The Pile)

Max Activating Token Index: 258

Text #11

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.0659. Min Act: -0.0001

Data Index: 483529 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.0671. Min Act: -0.0001

Data Index: 456050 (The Pile)

Max Activating Token Index: 138

Text #13

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.1084. Min Act: -0.0001

Data Index: 1343929 (The Pile)

Max Activating Token Index: 89

Text #14

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.0258. Min Act: -0.0001

Data Index: 415588 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.2068. Min Act: -0.0001

Data Index: 1495002 (The Pile)

Max Activating Token Index: 626

Text #16

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.0505. Min Act: -0.0001

Data Index: 784071 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.1107. Min Act: -0.0001

Data Index: 13785 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.0919. Min Act: -0.0001

Data Index: 1394851 (The Pile)

Max Activating Token Index: 401

Text #19

Max Range: 1.8320. Min Range: -1.8320

Max Act: 0.9828. Min Act: -0.0001

Data Index: 1310916 (The Pile)

Max Activating Token Index: 435