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

Dataset: The Pile

Neuron 155 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4986. Min Act: -0.0000

Data Index: 509730 (The Pile)

Max Activating Token Index: 288

Text #1

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1348101 (The Pile)

Max Activating Token Index: 883

Text #2

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4488. Min Act: -0.0000

Data Index: 235142 (The Pile)

Max Activating Token Index: 864

Text #3

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1667987 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4204. Min Act: -0.0000

Data Index: 975675 (The Pile)

Max Activating Token Index: 1020

Text #5

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1844197 (The Pile)

Max Activating Token Index: 683

Text #6

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3726. Min Act: -0.0000

Data Index: 790473 (The Pile)

Max Activating Token Index: 905

Text #7

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1563446 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1017842 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1161930 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3979. Min Act: -0.0000

Data Index: 170081 (The Pile)

Max Activating Token Index: 106

Text #11

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4037. Min Act: -0.0000

Data Index: 871946 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4057. Min Act: -0.0000

Data Index: 67601 (The Pile)

Max Activating Token Index: 867

Text #13

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1786960 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1531587 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3925. Min Act: -0.0000

Data Index: 794440 (The Pile)

Max Activating Token Index: 838

Text #16

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3953. Min Act: -0.0000

Data Index: 30955 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1159158 (The Pile)

Max Activating Token Index: 194

Text #18

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1346996 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 0.4986. Min Range: -0.4986

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1563048 (The Pile)

Max Activating Token Index: 71