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

Dataset: The Pile

Neuron 21 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: 3.2933. Min Range: -3.2933

Max Act: 3.2933. Min Act: -0.0000

Data Index: 1922357 (The Pile)

Max Activating Token Index: 174

Text #1

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.9081. Min Act: -0.0000

Data Index: 1008628 (The Pile)

Max Activating Token Index: 66

Text #2

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.9803. Min Act: -0.0000

Data Index: 1405453 (The Pile)

Max Activating Token Index: 314

Text #3

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.7903. Min Act: -0.0000

Data Index: 1745589 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.7852. Min Act: -0.0000

Data Index: 1069034 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.5632. Min Act: -0.0000

Data Index: 1087905 (The Pile)

Max Activating Token Index: 576

Text #6

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.6615. Min Act: -0.0000

Data Index: 1795410 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.7894. Min Act: -0.0000

Data Index: 1375285 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.5612. Min Act: -0.0000

Data Index: 784709 (The Pile)

Max Activating Token Index: 587

Text #9

Max Range: 3.2933. Min Range: -3.2933

Max Act: 1.9921. Min Act: -0.0000

Data Index: 1882883 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.5295. Min Act: -0.0000

Data Index: 513395 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.5124. Min Act: -0.0000

Data Index: 764721 (The Pile)

Max Activating Token Index: 401

Text #12

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.4368. Min Act: -0.0000

Data Index: 1461833 (The Pile)

Max Activating Token Index: 200

Text #13

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.2643. Min Act: -0.0000

Data Index: 1079903 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.5739. Min Act: -0.0000

Data Index: 574077 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.5614. Min Act: -0.0000

Data Index: 251487 (The Pile)

Max Activating Token Index: 250

Text #16

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.4192. Min Act: -0.0000

Data Index: 666391 (The Pile)

Max Activating Token Index: 220

Text #17

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.2039. Min Act: -0.0000

Data Index: 71925 (The Pile)

Max Activating Token Index: 848

Text #18

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.4083. Min Act: -0.0000

Data Index: 1041654 (The Pile)

Max Activating Token Index: 421

Text #19

Max Range: 3.2933. Min Range: -3.2933

Max Act: 2.5084. Min Act: -0.0000

Data Index: 424962 (The Pile)

Max Activating Token Index: 105