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

Dataset: The Pile

Neuron 644 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.3055. Min Act: -0.0000

Data Index: 26759 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.2532. Min Act: -0.0000

Data Index: 145321 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1085487 (The Pile)

Max Activating Token Index: 644

Text #3

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.1673. Min Act: -0.0000

Data Index: 1735738 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.0104. Min Act: -0.0000

Data Index: 1231121 (The Pile)

Max Activating Token Index: 367

Text #5

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.0930. Min Act: -0.0000

Data Index: 862452 (The Pile)

Max Activating Token Index: 32

Text #6

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1617445 (The Pile)

Max Activating Token Index: 981

Text #7

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.0291. Min Act: -0.0000

Data Index: 1991233 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.8863. Min Act: -0.0000

Data Index: 636672 (The Pile)

Max Activating Token Index: 97

Text #9

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1832447 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9425. Min Act: -0.0000

Data Index: 881413 (The Pile)

Max Activating Token Index: 343

Text #11

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1842387 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1105152 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.8936. Min Act: -0.0000

Data Index: 996632 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.0054. Min Act: -0.0000

Data Index: 1432802 (The Pile)

Max Activating Token Index: 79

Text #15

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9690. Min Act: -0.0000

Data Index: 892468 (The Pile)

Max Activating Token Index: 233

Text #16

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9031. Min Act: -0.0000

Data Index: 735782 (The Pile)

Max Activating Token Index: 249

Text #17

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1738195 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.8724. Min Act: -0.0000

Data Index: 428969 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1961658 (The Pile)

Max Activating Token Index: 735