Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2394 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1207220 (The Pile)

Max Activating Token Index: 68

Text #1

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4106. Min Act: -0.0000

Data Index: 875685 (The Pile)

Max Activating Token Index: 707

Text #2

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4033. Min Act: -0.0000

Data Index: 949314 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1610269 (The Pile)

Max Activating Token Index: 227

Text #4

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1102436 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3574. Min Act: -0.0000

Data Index: 294529 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1305768 (The Pile)

Max Activating Token Index: 485

Text #7

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1205114 (The Pile)

Max Activating Token Index: 624

Text #8

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1760013 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1541504 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1507816 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3497. Min Act: -0.0000

Data Index: 92236 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3734. Min Act: -0.0000

Data Index: 185732 (The Pile)

Max Activating Token Index: 622

Text #13

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3206. Min Act: -0.0000

Data Index: 1004481 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3522. Min Act: -0.0000

Data Index: 1975641 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1709727 (The Pile)

Max Activating Token Index: 340

Text #16

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3021. Min Act: -0.0000

Data Index: 187011 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3394. Min Act: -0.0000

Data Index: 622910 (The Pile)

Max Activating Token Index: 662

Text #18

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.2932. Min Act: -0.0000

Data Index: 216195 (The Pile)

Max Activating Token Index: 739

Text #19

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1466231 (The Pile)

Max Activating Token Index: 525