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

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

Neuron 4470 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.5892. Min Act: -0.0001

Data Index: 154871 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.6880. Min Act: -0.0001

Data Index: 713480 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.5156. Min Act: -0.0001

Data Index: 727557 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.5941. Min Act: -0.0001

Data Index: 422028 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.5396. Min Act: -0.0001

Data Index: 739487 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.4463. Min Act: -0.0001

Data Index: 1123378 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.5085. Min Act: -0.0001

Data Index: 419477 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.3715. Min Act: -0.0001

Data Index: 841956 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.4416. Min Act: -0.0001

Data Index: 570338 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.3901. Min Act: -0.0001

Data Index: 145626 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2982. Min Act: -0.0001

Data Index: 754917 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.3361. Min Act: -0.0001

Data Index: 840926 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.3164. Min Act: -0.0001

Data Index: 766202 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2741. Min Act: -0.0001

Data Index: 869149 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2618. Min Act: -0.0001

Data Index: 38958 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.1949. Min Act: -0.0001

Data Index: 653057 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.1853. Min Act: -0.0001

Data Index: 275371 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2504. Min Act: -0.0001

Data Index: 127085 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2451. Min Act: -0.0001

Data Index: 87112 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.1984. Min Act: -0.0001

Data Index: 183694 (C4 (Web Text))

Max Activating Token Index: 552