Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 370 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.9090. Min Act: -0.0000

Data Index: 516329 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.9141. Min Act: -0.0000

Data Index: 1339891 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.7931. Min Act: -0.0000

Data Index: 835796 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.7736. Min Act: -0.0000

Data Index: 54016 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.7667. Min Act: -0.0000

Data Index: 214704 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6918. Min Act: -0.0000

Data Index: 510571 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.7013. Min Act: -0.0000

Data Index: 81108 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5761. Min Act: -0.0000

Data Index: 110826 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6329. Min Act: -0.0000

Data Index: 557022 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6249. Min Act: -0.0000

Data Index: 173254 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6249. Min Act: -0.0000

Data Index: 505449 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6352. Min Act: -0.0000

Data Index: 750020 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5755. Min Act: -0.0000

Data Index: 263404 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6069. Min Act: -0.0000

Data Index: 216811 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5862. Min Act: -0.0000

Data Index: 97679 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5606. Min Act: -0.0000

Data Index: 885888 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5846. Min Act: -0.0000

Data Index: 114551 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5857. Min Act: -0.0000

Data Index: 312733 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5710. Min Act: -0.0000

Data Index: 230938 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5368. Min Act: -0.0000

Data Index: 761099 (C4 (Web Text))

Max Activating Token Index: 72