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

Dataset: The Pile

Neuron 3751 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: 0.6809. Min Range: -0.6809

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1311905 (The Pile)

Max Activating Token Index: 93

Text #1

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1083544 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1161919 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5613. Min Act: -0.0000

Data Index: 210058 (The Pile)

Max Activating Token Index: 42

Text #4

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5152. Min Act: -0.0001

Data Index: 672830 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4673. Min Act: -0.0000

Data Index: 62558 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1817583 (The Pile)

Max Activating Token Index: 885

Text #7

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1952534 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4941. Min Act: -0.0000

Data Index: 667282 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1139168 (The Pile)

Max Activating Token Index: 934

Text #10

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1361082 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1630856 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4865. Min Act: -0.0000

Data Index: 309688 (The Pile)

Max Activating Token Index: 481

Text #13

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4557. Min Act: -0.0000

Data Index: 964229 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1554273 (The Pile)

Max Activating Token Index: 779

Text #15

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5084. Min Act: -0.0000

Data Index: 450938 (The Pile)

Max Activating Token Index: 357

Text #16

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1424697 (The Pile)

Max Activating Token Index: 140

Text #17

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4631. Min Act: -0.0000

Data Index: 354562 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5007. Min Act: -0.0000

Data Index: 533034 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4565. Min Act: -0.0000

Data Index: 978717 (The Pile)

Max Activating Token Index: 638