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

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

Neuron 1607 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1195483 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0786. Min Act: -0.0000

Data Index: 71309 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0761. Min Act: -0.0000

Data Index: 750495 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1329747 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0676. Min Act: -0.0001

Data Index: 215140 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0778. Min Act: -0.0001

Data Index: 319407 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1335340 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1220252 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0689. Min Act: -0.0001

Data Index: 992340 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1286991 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0661. Min Act: -0.0001

Data Index: 593042 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0653. Min Act: -0.0000

Data Index: 1298414 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0670. Min Act: -0.0000

Data Index: 944416 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1067250 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0636. Min Act: -0.0000

Data Index: 209746 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0636. Min Act: -0.0001

Data Index: 582658 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0658. Min Act: -0.0001

Data Index: 949093 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1314365 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1016507 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0616. Min Act: -0.0000

Data Index: 874449 (C4 (Web Text))

Max Activating Token Index: 613