Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1688 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1693202 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1063014 (The Pile)

Max Activating Token Index: 281

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1012. Min Act: -0.0002

Data Index: 1255141 (The Pile)

Max Activating Token Index: 567

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0968. Min Act: -0.0001

Data Index: 205989 (The Pile)

Max Activating Token Index: 412

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1227632 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0975. Min Act: -0.0002

Data Index: 799649 (The Pile)

Max Activating Token Index: 140

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1720242 (The Pile)

Max Activating Token Index: 705

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1768862 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0949. Min Act: -0.0002

Data Index: 39501 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1161626 (The Pile)

Max Activating Token Index: 423

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1643675 (The Pile)

Max Activating Token Index: 674

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1474377 (The Pile)

Max Activating Token Index: 720

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0932. Min Act: -0.0002

Data Index: 2221 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1866219 (The Pile)

Max Activating Token Index: 284

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1335244 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1594939 (The Pile)

Max Activating Token Index: 343

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0921. Min Act: -0.0002

Data Index: 68886 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0920. Min Act: -0.0001

Data Index: 1901938 (The Pile)

Max Activating Token Index: 208

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0919. Min Act: -0.0002

Data Index: 886426 (The Pile)

Max Activating Token Index: 217

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1513583 (The Pile)

Max Activating Token Index: 623