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

Dataset: The Pile

Neuron 3824 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1843516 (The Pile)

Max Activating Token Index: 314

Text #1

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1510987 (The Pile)

Max Activating Token Index: 723

Text #2

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.8552. Min Act: -0.0000

Data Index: 385055 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7725. Min Act: -0.0000

Data Index: 447595 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7699. Min Act: -0.0000

Data Index: 897496 (The Pile)

Max Activating Token Index: 231

Text #5

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6881. Min Act: -0.0000

Data Index: 558888 (The Pile)

Max Activating Token Index: 1007

Text #6

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1943608 (The Pile)

Max Activating Token Index: 445

Text #7

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1705217 (The Pile)

Max Activating Token Index: 9

Text #8

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1175348 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1574825 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1254257 (The Pile)

Max Activating Token Index: 176

Text #11

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1446648 (The Pile)

Max Activating Token Index: 481

Text #12

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1355651 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6550. Min Act: -0.0000

Data Index: 554674 (The Pile)

Max Activating Token Index: 51

Text #14

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1883995 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1958821 (The Pile)

Max Activating Token Index: 524

Text #16

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6517. Min Act: -0.0000

Data Index: 487661 (The Pile)

Max Activating Token Index: 77

Text #17

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6289. Min Act: -0.0000

Data Index: 284198 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1088274 (The Pile)

Max Activating Token Index: 1014

Text #19

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6414. Min Act: -0.0000

Data Index: 309067 (The Pile)

Max Activating Token Index: 644