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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 114 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4935. Min Act: -0.0002

Data Index: 1121463 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4781. Min Act: -0.0002

Data Index: 1341008 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4720. Min Act: -0.0003

Data Index: 651418 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4608. Min Act: -0.0002

Data Index: 406694 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4575. Min Act: -0.0003

Data Index: 856357 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4629. Min Act: -0.0002

Data Index: 468850 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4293. Min Act: -0.0002

Data Index: 225709 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4406. Min Act: -0.0002

Data Index: 371192 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4253. Min Act: -0.0002

Data Index: 508865 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4130. Min Act: -0.0002

Data Index: 578128 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3990. Min Act: -0.0003

Data Index: 907151 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3936. Min Act: -0.0002

Data Index: 798734 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4117. Min Act: -0.0003

Data Index: 262012 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3974. Min Act: -0.0003

Data Index: 764002 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3937. Min Act: -0.0002

Data Index: 588129 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3900. Min Act: -0.0003

Data Index: 49800 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3885. Min Act: -0.0003

Data Index: 21241 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3748. Min Act: -0.0002

Data Index: 181875 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3875. Min Act: -0.0003

Data Index: 921235 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3876. Min Act: -0.0002

Data Index: 741646 (C4 (Web Text))

Max Activating Token Index: 966