Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3918 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.2166. Min Act: -0.0001

Data Index: 13820 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0435. Min Act: -0.0001

Data Index: 935962 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.1627. Min Act: -0.0001

Data Index: 1173346 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.1701. Min Act: -0.0001

Data Index: 758873 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.1262. Min Act: -0.0001

Data Index: 581154 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.1423. Min Act: -0.0001

Data Index: 318365 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.1699. Min Act: -0.0001

Data Index: 607413 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.2085. Min Act: -0.0001

Data Index: 1305043 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0793. Min Act: -0.0001

Data Index: 8580 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0454. Min Act: -0.0001

Data Index: 394648 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0665. Min Act: -0.0001

Data Index: 644915 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0969. Min Act: -0.0001

Data Index: 1235544 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9979. Min Act: -0.0001

Data Index: 658463 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9685. Min Act: -0.0001

Data Index: 104068 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0099. Min Act: -0.0001

Data Index: 780672 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9836. Min Act: -0.0001

Data Index: 1167005 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0617. Min Act: -0.0001

Data Index: 420234 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9629. Min Act: -0.0001

Data Index: 877248 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9338. Min Act: -0.0001

Data Index: 537863 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9912. Min Act: -0.0001

Data Index: 12552 (C4 (Web Text))

Max Activating Token Index: 755