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

Dataset: The Pile

Neuron 3878 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5663. Min Range: -3.5663

Max Act: 3.5663. Min Act: -0.0000

Data Index: 1650780 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 3.5663. Min Range: -3.5663

Max Act: 3.3715. Min Act: -0.0000

Data Index: 340989 (The Pile)

Max Activating Token Index: 946

Text #2

Max Range: 3.5663. Min Range: -3.5663

Max Act: 3.1398. Min Act: -0.0000

Data Index: 79664 (The Pile)

Max Activating Token Index: 899

Text #3

Max Range: 3.5663. Min Range: -3.5663

Max Act: 3.3640. Min Act: -0.0000

Data Index: 1934920 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 3.5663. Min Range: -3.5663

Max Act: 3.4859. Min Act: -0.0000

Data Index: 763000 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 3.5663. Min Range: -3.5663

Max Act: 3.3192. Min Act: -0.0000

Data Index: 1160022 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 3.5663. Min Range: -3.5663

Max Act: 3.2649. Min Act: -0.0000

Data Index: 1919485 (The Pile)

Max Activating Token Index: 450

Text #7

Max Range: 3.5663. Min Range: -3.5663

Max Act: 2.8591. Min Act: -0.0000

Data Index: 571595 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 3.5663. Min Range: -3.5663

Max Act: 3.0371. Min Act: -0.0000

Data Index: 1037052 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 3.5663. Min Range: -3.5663

Max Act: 2.8678. Min Act: -0.0000

Data Index: 627466 (The Pile)

Max Activating Token Index: 780

Text #10

Max Range: 3.5663. Min Range: -3.5663

Max Act: 3.1349. Min Act: -0.0000

Data Index: 1141968 (The Pile)

Max Activating Token Index: 236

Text #11

Max Range: 3.5663. Min Range: -3.5663

Max Act: 3.1654. Min Act: -0.0000

Data Index: 1802185 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 3.5663. Min Range: -3.5663

Max Act: 2.9740. Min Act: -0.0000

Data Index: 1624896 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 3.5663. Min Range: -3.5663

Max Act: 3.1279. Min Act: -0.0000

Data Index: 780544 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 3.5663. Min Range: -3.5663

Max Act: 2.8315. Min Act: -0.0000

Data Index: 755344 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 3.5663. Min Range: -3.5663

Max Act: 2.9335. Min Act: -0.0000

Data Index: 352647 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 3.5663. Min Range: -3.5663

Max Act: 2.7917. Min Act: -0.0000

Data Index: 531537 (The Pile)

Max Activating Token Index: 192

Text #17

Max Range: 3.5663. Min Range: -3.5663

Max Act: 3.0365. Min Act: -0.0000

Data Index: 311638 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 3.5663. Min Range: -3.5663

Max Act: 2.7395. Min Act: -0.0000

Data Index: 1255270 (The Pile)

Max Activating Token Index: 72

Text #19

Max Range: 3.5663. Min Range: -3.5663

Max Act: 2.8568. Min Act: -0.0000

Data Index: 1400481 (The Pile)

Max Activating Token Index: 107