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

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

Neuron 5 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: 0.9262. Min Range: -0.9262

Max Act: 0.8985. Min Act: -0.0001

Data Index: 692722 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.8695. Min Act: -0.0001

Data Index: 1330573 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.9262. Min Act: -0.0001

Data Index: 334274 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.8684. Min Act: -0.0001

Data Index: 501680 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.8875. Min Act: -0.0001

Data Index: 912061 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.8953. Min Act: -0.0001

Data Index: 498019 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.8147. Min Act: -0.0001

Data Index: 1121202 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.8488. Min Act: -0.0001

Data Index: 868681 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.8698. Min Act: -0.0001

Data Index: 844803 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.7524. Min Act: -0.0001

Data Index: 1074616 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.7995. Min Act: -0.0001

Data Index: 41798 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.8242. Min Act: -0.0001

Data Index: 296125 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.7712. Min Act: -0.0001

Data Index: 1057854 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.8156. Min Act: -0.0001

Data Index: 184384 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.8131. Min Act: -0.0001

Data Index: 1286689 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.7660. Min Act: -0.0001

Data Index: 1005580 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.8012. Min Act: -0.0001

Data Index: 1192001 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.8000. Min Act: -0.0001

Data Index: 685051 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.7993. Min Act: -0.0001

Data Index: 581435 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.9262. Min Range: -0.9262

Max Act: 0.7983. Min Act: -0.0001

Data Index: 661065 (C4 (Web Text))

Max Activating Token Index: 418