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

Dataset: The Pile

Neuron 4896 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: 0.1520. Min Range: -0.1520

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1398774 (The Pile)

Max Activating Token Index: 627

Text #1

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1473186 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1502067 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1843004 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1814392 (The Pile)

Max Activating Token Index: 436

Text #5

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1496548 (The Pile)

Max Activating Token Index: 868

Text #6

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1074. Min Act: -0.0000

Data Index: 371482 (The Pile)

Max Activating Token Index: 117

Text #7

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1710408 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0962. Min Act: -0.0000

Data Index: 446862 (The Pile)

Max Activating Token Index: 739

Text #9

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0810. Min Act: -0.0000

Data Index: 541256 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0942. Min Act: -0.0000

Data Index: 260265 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0906. Min Act: -0.0000

Data Index: 881018 (The Pile)

Max Activating Token Index: 546

Text #12

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0960. Min Act: -0.0000

Data Index: 846627 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1351473 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1414391 (The Pile)

Max Activating Token Index: 920

Text #15

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1435125 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1610233 (The Pile)

Max Activating Token Index: 504

Text #17

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0936. Min Act: -0.0000

Data Index: 959618 (The Pile)

Max Activating Token Index: 547

Text #18

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1669635 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0881. Min Act: -0.0000

Data Index: 1991187 (The Pile)

Max Activating Token Index: 700