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

Dataset: The Pile

Neuron 755 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: 0.5928. Min Range: -0.5928

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1068495 (The Pile)

Max Activating Token Index: 637

Text #1

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4451. Min Act: -0.0000

Data Index: 262112 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1212912 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.3925. Min Act: -0.0000

Data Index: 867573 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4378. Min Act: 0.0000

Data Index: 1220183 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4470. Min Act: -0.0000

Data Index: 865040 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1794172 (The Pile)

Max Activating Token Index: 359

Text #7

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4088. Min Act: 0.0000

Data Index: 940217 (The Pile)

Max Activating Token Index: 28

Text #8

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1257411 (The Pile)

Max Activating Token Index: 577

Text #9

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1121598 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1630404 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1029283 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1288173 (The Pile)

Max Activating Token Index: 302

Text #13

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4046. Min Act: -0.0000

Data Index: 931672 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1580803 (The Pile)

Max Activating Token Index: 490

Text #15

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1292445 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1717463 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4109. Min Act: -0.0000

Data Index: 153177 (The Pile)

Max Activating Token Index: 1002

Text #18

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4076. Min Act: -0.0000

Data Index: 283789 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1304335 (The Pile)

Max Activating Token Index: 221