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

Dataset: The Pile

Neuron 3116 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.8881. Min Act: -0.0000

Data Index: 608933 (The Pile)

Max Activating Token Index: 812

Text #1

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.7789. Min Act: -0.0000

Data Index: 605634 (The Pile)

Max Activating Token Index: 535

Text #2

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6997. Min Act: -0.0000

Data Index: 437048 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6835. Min Act: -0.0000

Data Index: 266299 (The Pile)

Max Activating Token Index: 968

Text #4

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6380. Min Act: -0.0000

Data Index: 784188 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1312779 (The Pile)

Max Activating Token Index: 899

Text #6

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1940754 (The Pile)

Max Activating Token Index: 561

Text #7

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6155. Min Act: -0.0000

Data Index: 53200 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1056560 (The Pile)

Max Activating Token Index: 1022

Text #9

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1355622 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1154777 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1236472 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1749823 (The Pile)

Max Activating Token Index: 298

Text #13

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.5727. Min Act: -0.0000

Data Index: 124024 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6306. Min Act: -0.0000

Data Index: 669775 (The Pile)

Max Activating Token Index: 388

Text #15

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1556639 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.5966. Min Act: -0.0000

Data Index: 956087 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.5566. Min Act: -0.0000

Data Index: 817538 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1749361 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 0.8881. Min Range: -0.8881

Max Act: 0.5216. Min Act: -0.0000

Data Index: 578373 (The Pile)

Max Activating Token Index: 479