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

Dataset: The Pile

Neuron 5007 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: 1.1209. Min Range: -1.1209

Max Act: 1.1209. Min Act: -0.0000

Data Index: 275340 (The Pile)

Max Activating Token Index: 294

Text #1

Max Range: 1.1209. Min Range: -1.1209

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1309044 (The Pile)

Max Activating Token Index: 442

Text #2

Max Range: 1.1209. Min Range: -1.1209

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1395530 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1040506 (The Pile)

Max Activating Token Index: 548

Text #4

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1094663 (The Pile)

Max Activating Token Index: 52

Text #5

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9513. Min Act: -0.0000

Data Index: 975084 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9236. Min Act: -0.0000

Data Index: 635704 (The Pile)

Max Activating Token Index: 62

Text #7

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8380. Min Act: -0.0000

Data Index: 711622 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1967639 (The Pile)

Max Activating Token Index: 870

Text #9

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1084720 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1411976 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8824. Min Act: -0.0000

Data Index: 205593 (The Pile)

Max Activating Token Index: 187

Text #12

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8733. Min Act: -0.0000

Data Index: 48365 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8386. Min Act: -0.0000

Data Index: 233118 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8653. Min Act: -0.0000

Data Index: 62924 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8921. Min Act: -0.0000

Data Index: 323709 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8283. Min Act: -0.0000

Data Index: 191566 (The Pile)

Max Activating Token Index: 120

Text #17

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8764. Min Act: -0.0000

Data Index: 1152047 (The Pile)

Max Activating Token Index: 891

Text #18

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.7915. Min Act: -0.0000

Data Index: 944596 (The Pile)

Max Activating Token Index: 232

Text #19

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1110692 (The Pile)

Max Activating Token Index: 573