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

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

Neuron 93 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1000500 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1203516 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1070491 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0933. Min Act: -0.0001

Data Index: 995178 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1198275 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1047181 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1011. Min Act: -0.0001

Data Index: 17364 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0868. Min Act: -0.0001

Data Index: 522375 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1238838 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0981. Min Act: -0.0001

Data Index: 576355 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0878. Min Act: -0.0001

Data Index: 286359 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0847. Min Act: -0.0001

Data Index: 1044489 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0867. Min Act: -0.0001

Data Index: 36403 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0896. Min Act: -0.0001

Data Index: 518927 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0813. Min Act: -0.0001

Data Index: 107774 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1003327 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0782. Min Act: -0.0001

Data Index: 626784 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1042957 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0839. Min Act: -0.0001

Data Index: 590542 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0771. Min Act: -0.0001

Data Index: 724984 (C4 (Web Text))

Max Activating Token Index: 363