Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2070 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4493. Min Act: 0.0000

Data Index: 651768 (The Pile)

Max Activating Token Index: 877

Text #1

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1439997 (The Pile)

Max Activating Token Index: 133

Text #2

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4348. Min Act: -0.0000

Data Index: 844580 (The Pile)

Max Activating Token Index: 526

Text #3

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4156. Min Act: -0.0000

Data Index: 247352 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3997. Min Act: -0.0000

Data Index: 174042 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1762523 (The Pile)

Max Activating Token Index: 943

Text #6

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1396170 (The Pile)

Max Activating Token Index: 338

Text #7

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3937. Min Act: -0.0000

Data Index: 523182 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1663573 (The Pile)

Max Activating Token Index: 161

Text #9

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3775. Min Act: -0.0000

Data Index: 692202 (The Pile)

Max Activating Token Index: 197

Text #10

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3905. Min Act: -0.0000

Data Index: 81571 (The Pile)

Max Activating Token Index: 506

Text #11

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1306924 (The Pile)

Max Activating Token Index: 796

Text #12

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3909. Min Act: -0.0000

Data Index: 457703 (The Pile)

Max Activating Token Index: 144

Text #13

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3740. Min Act: -0.0000

Data Index: 797148 (The Pile)

Max Activating Token Index: 645

Text #14

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3627. Min Act: -0.0000

Data Index: 1768734 (The Pile)

Max Activating Token Index: 900

Text #15

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3540. Min Act: -0.0000

Data Index: 60289 (The Pile)

Max Activating Token Index: 21

Text #16

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3760. Min Act: -0.0000

Data Index: 342448 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3756. Min Act: -0.0000

Data Index: 88917 (The Pile)

Max Activating Token Index: 523

Text #18

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3845. Min Act: -0.0000

Data Index: 901599 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3425. Min Act: 0.0000

Data Index: 1613699 (The Pile)

Max Activating Token Index: 843