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

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

Neuron 4185 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1135. Min Act: -0.0002

Data Index: 569552 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0983. Min Act: -0.0002

Data Index: 735118 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0964. Min Act: -0.0002

Data Index: 991205 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1012. Min Act: -0.0002

Data Index: 814900 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1292043 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1011. Min Act: -0.0002

Data Index: 151848 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0998. Min Act: -0.0002

Data Index: 984347 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0937. Min Act: -0.0002

Data Index: 1211235 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1062961 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0882. Min Act: -0.0002

Data Index: 914181 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0881. Min Act: -0.0002

Data Index: 298444 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0926. Min Act: -0.0002

Data Index: 723794 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0788. Min Act: -0.0002

Data Index: 679360 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0986. Min Act: -0.0002

Data Index: 242907 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0898. Min Act: -0.0002

Data Index: 522560 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0956. Min Act: -0.0002

Data Index: 152626 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0906. Min Act: -0.0002

Data Index: 173011 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0914. Min Act: -0.0002

Data Index: 858159 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0878. Min Act: -0.0002

Data Index: 720049 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1058406 (C4 (Web Text))

Max Activating Token Index: 41