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

Dataset: The Pile

Neuron 1252 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: 0.3144. Min Range: -0.3144

Max Act: 0.2794. Min Act: -0.0001

Data Index: 323403 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1065720 (The Pile)

Max Activating Token Index: 982

Text #2

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2973. Min Act: -0.0000

Data Index: 59091 (The Pile)

Max Activating Token Index: 319

Text #3

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2881. Min Act: -0.0000

Data Index: 433681 (The Pile)

Max Activating Token Index: 279

Text #4

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2892. Min Act: -0.0001

Data Index: 484673 (The Pile)

Max Activating Token Index: 270

Text #5

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1753546 (The Pile)

Max Activating Token Index: 487

Text #6

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2359. Min Act: -0.0000

Data Index: 350139 (The Pile)

Max Activating Token Index: 478

Text #7

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2439. Min Act: -0.0000

Data Index: 57697 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1066482 (The Pile)

Max Activating Token Index: 87

Text #9

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1855649 (The Pile)

Max Activating Token Index: 678

Text #10

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2292. Min Act: -0.0000

Data Index: 489972 (The Pile)

Max Activating Token Index: 856

Text #11

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1306512 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1591104 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2157. Min Act: -0.0000

Data Index: 948839 (The Pile)

Max Activating Token Index: 260

Text #14

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1664697 (The Pile)

Max Activating Token Index: 524

Text #15

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2149. Min Act: -0.0000

Data Index: 333912 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1978. Min Act: -0.0000

Data Index: 402107 (The Pile)

Max Activating Token Index: 583

Text #17

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1923009 (The Pile)

Max Activating Token Index: 621

Text #18

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1917644 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2090. Min Act: -0.0000

Data Index: 18505 (The Pile)

Max Activating Token Index: 442