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

Dataset: The Pile

Neuron 1440 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0434. Min Range: -1.0434

Max Act: 1.0358. Min Act: -0.0000

Data Index: 462172 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 1.0434. Min Range: -1.0434

Max Act: 1.0434. Min Act: -0.0000

Data Index: 695948 (The Pile)

Max Activating Token Index: 191

Text #2

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9712. Min Act: -0.0000

Data Index: 552433 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 1.0434. Min Range: -1.0434

Max Act: 1.0344. Min Act: -0.0000

Data Index: 130570 (The Pile)

Max Activating Token Index: 218

Text #4

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9985. Min Act: -0.0000

Data Index: 1714454 (The Pile)

Max Activating Token Index: 459

Text #5

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9715. Min Act: -0.0000

Data Index: 1504951 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1677770 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9161. Min Act: -0.0000

Data Index: 927007 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1916500 (The Pile)

Max Activating Token Index: 231

Text #9

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8989. Min Act: -0.0000

Data Index: 885631 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8880. Min Act: -0.0000

Data Index: 965237 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8883. Min Act: -0.0000

Data Index: 1788150 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9175. Min Act: -0.0000

Data Index: 1319742 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1080236 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1253077 (The Pile)

Max Activating Token Index: 740

Text #15

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1789069 (The Pile)

Max Activating Token Index: 828

Text #16

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8490. Min Act: -0.0000

Data Index: 460811 (The Pile)

Max Activating Token Index: 736

Text #17

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.9421. Min Act: -0.0000

Data Index: 566964 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8466. Min Act: -0.0000

Data Index: 420377 (The Pile)

Max Activating Token Index: 359

Text #19

Max Range: 1.0434. Min Range: -1.0434

Max Act: 0.8101. Min Act: -0.0000

Data Index: 43766 (The Pile)

Max Activating Token Index: 316