Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1082 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.8927. Min Act: -0.0003

Data Index: 1163864 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7067. Min Act: -0.0003

Data Index: 749765 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7813. Min Act: -0.0003

Data Index: 314785 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7172. Min Act: -0.0003

Data Index: 947527 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6976. Min Act: -0.0003

Data Index: 690178 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6563. Min Act: -0.0003

Data Index: 453339 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7307. Min Act: -0.0003

Data Index: 983524 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6434. Min Act: -0.0003

Data Index: 1310659 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6962. Min Act: -0.0003

Data Index: 709182 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6907. Min Act: -0.0003

Data Index: 967991 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6608. Min Act: -0.0003

Data Index: 81310 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6868. Min Act: -0.0003

Data Index: 747562 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6321. Min Act: -0.0003

Data Index: 1132854 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6555. Min Act: -0.0003

Data Index: 615548 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5932. Min Act: -0.0003

Data Index: 209720 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6637. Min Act: -0.0003

Data Index: 1153382 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5773. Min Act: -0.0003

Data Index: 1075 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6244. Min Act: -0.0003

Data Index: 12489 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6252. Min Act: -0.0003

Data Index: 1193201 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5922. Min Act: -0.0003

Data Index: 997636 (C4 (Web Text))

Max Activating Token Index: 527