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

Dataset: The Pile

Neuron 1642 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6417. Min Act: -0.0000

Data Index: 981960 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6614. Min Act: -0.0000

Data Index: 867295 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5593. Min Act: -0.0000

Data Index: 733253 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5548. Min Act: -0.0000

Data Index: 243981 (The Pile)

Max Activating Token Index: 750

Text #4

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1742500 (The Pile)

Max Activating Token Index: 701

Text #5

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6608. Min Act: -0.0000

Data Index: 629434 (The Pile)

Max Activating Token Index: 271

Text #6

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5154. Min Act: -0.0000

Data Index: 912248 (The Pile)

Max Activating Token Index: 196

Text #7

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1464478 (The Pile)

Max Activating Token Index: 216

Text #8

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6643. Min Act: -0.0000

Data Index: 37700 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1282693 (The Pile)

Max Activating Token Index: 749

Text #10

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5575. Min Act: -0.0000

Data Index: 1237005 (The Pile)

Max Activating Token Index: 352

Text #11

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5354. Min Act: -0.0000

Data Index: 788716 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5438. Min Act: -0.0000

Data Index: 946969 (The Pile)

Max Activating Token Index: 141

Text #13

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1354141 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5117. Min Act: -0.0000

Data Index: 140366 (The Pile)

Max Activating Token Index: 601

Text #15

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1854737 (The Pile)

Max Activating Token Index: 264

Text #16

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4844. Min Act: -0.0000

Data Index: 209865 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4635. Min Act: -0.0000

Data Index: 866161 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1540137 (The Pile)

Max Activating Token Index: 714

Text #19

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4552. Min Act: -0.0000

Data Index: 589493 (The Pile)

Max Activating Token Index: 23