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

Dataset: The Pile

Neuron 2112 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.6767. Min Act: -0.0000

Data Index: 609007 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5672. Min Act: 0.0001

Data Index: 713298 (The Pile)

Max Activating Token Index: 201

Text #2

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1395586 (The Pile)

Max Activating Token Index: 866

Text #3

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1965964 (The Pile)

Max Activating Token Index: 17

Text #4

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1446242 (The Pile)

Max Activating Token Index: 941

Text #5

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1445526 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1891151 (The Pile)

Max Activating Token Index: 855

Text #7

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1120400 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1045368 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.3854. Min Act: -0.0000

Data Index: 1300924 (The Pile)

Max Activating Token Index: 940

Text #10

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1062265 (The Pile)

Max Activating Token Index: 161

Text #11

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1284724 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4447. Min Act: -0.0000

Data Index: 48445 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4016. Min Act: -0.0000

Data Index: 105664 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1520196 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4052. Min Act: -0.0000

Data Index: 821070 (The Pile)

Max Activating Token Index: 10

Text #16

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.3906. Min Act: -0.0000

Data Index: 50666 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4374. Min Act: -0.0000

Data Index: 743650 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1601125 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1996119 (The Pile)

Max Activating Token Index: 592