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

Dataset: The Pile

Neuron 219 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: 0.4131. Min Range: -0.4131

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1758515 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3925. Min Act: -0.0000

Data Index: 211000 (The Pile)

Max Activating Token Index: 874

Text #2

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3582. Min Act: -0.0000

Data Index: 998184 (The Pile)

Max Activating Token Index: 819

Text #3

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3827. Min Act: -0.0000

Data Index: 610938 (The Pile)

Max Activating Token Index: 768

Text #4

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1681401 (The Pile)

Max Activating Token Index: 686

Text #5

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1462446 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3911. Min Act: -0.0000

Data Index: 139745 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1890734 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3327. Min Act: -0.0000

Data Index: 478142 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3596. Min Act: -0.0000

Data Index: 157810 (The Pile)

Max Activating Token Index: 78

Text #10

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1890080 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1521974 (The Pile)

Max Activating Token Index: 464

Text #12

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3338. Min Act: -0.0000

Data Index: 494880 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3525. Min Act: -0.0000

Data Index: 235911 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3522. Min Act: -0.0000

Data Index: 980820 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3543. Min Act: -0.0000

Data Index: 801631 (The Pile)

Max Activating Token Index: 879

Text #16

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1819077 (The Pile)

Max Activating Token Index: 252

Text #17

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1671526 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1403223 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1759631 (The Pile)

Max Activating Token Index: 763