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

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

Neuron 2900 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0002

Data Index: 793070 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0002

Data Index: 806268 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0002

Data Index: 402661 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0065. Min Act: -0.0002

Data Index: 878807 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1032507 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0002

Data Index: 36989 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0065. Min Act: -0.0002

Data Index: 717250 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1230184 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0062. Min Act: -0.0002

Data Index: 20074 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 732461 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1048155 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0061. Min Act: -0.0002

Data Index: 482456 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0061. Min Act: -0.0002

Data Index: 154362 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0061. Min Act: -0.0002

Data Index: 774072 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 830 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 940890 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1289033 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0002

Data Index: 21257 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0002

Data Index: 955522 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0002

Data Index: 55146 (C4 (Web Text))

Max Activating Token Index: 186