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

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

Neuron 2320 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1880. Min Act: -0.0003

Data Index: 479825 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1713. Min Act: -0.0003

Data Index: 702291 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1797. Min Act: -0.0003

Data Index: 326790 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1846. Min Act: -0.0003

Data Index: 174646 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1661. Min Act: -0.0003

Data Index: 1066293 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1588. Min Act: -0.0003

Data Index: 1145127 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1646. Min Act: -0.0004

Data Index: 1344088 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1757. Min Act: -0.0003

Data Index: 153026 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1576. Min Act: -0.0003

Data Index: 886177 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1627. Min Act: -0.0003

Data Index: 950282 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1731. Min Act: -0.0003

Data Index: 929275 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1786. Min Act: -0.0003

Data Index: 445265 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1662. Min Act: -0.0004

Data Index: 880084 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1764. Min Act: -0.0003

Data Index: 63360 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1638. Min Act: -0.0003

Data Index: 1334565 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1960. Min Act: -0.0003

Data Index: 1073491 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1529. Min Act: -0.0003

Data Index: 141130 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1577. Min Act: -0.0003

Data Index: 773543 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1632. Min Act: -0.0003

Data Index: 58052 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1632. Min Act: -0.0003

Data Index: 1001387 (C4 (Web Text))

Max Activating Token Index: 701