Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1969 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.9441. Min Act: -0.0000

Data Index: 406601 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.9134. Min Act: -0.0000

Data Index: 568264 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1075956 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.9037. Min Act: -0.0000

Data Index: 283583 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.8468. Min Act: -0.0000

Data Index: 857113 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.8488. Min Act: -0.0000

Data Index: 15288 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.8042. Min Act: -0.0000

Data Index: 458366 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.7489. Min Act: -0.0000

Data Index: 778502 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.8011. Min Act: -0.0000

Data Index: 858155 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.8014. Min Act: -0.0000

Data Index: 836991 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.8118. Min Act: -0.0000

Data Index: 878078 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.7806. Min Act: -0.0000

Data Index: 288676 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.7573. Min Act: -0.0000

Data Index: 598962 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.7487. Min Act: -0.0000

Data Index: 148840 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.7659. Min Act: -0.0000

Data Index: 957703 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.7708. Min Act: -0.0000

Data Index: 363502 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.7589. Min Act: -0.0000

Data Index: 78255 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.7457. Min Act: -0.0000

Data Index: 737029 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1334595 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.9596. Min Range: -0.9596

Max Act: 0.7248. Min Act: -0.0000

Data Index: 510620 (C4 (Web Text))

Max Activating Token Index: 338