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

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

Neuron 3999 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.7221. Min Act: -0.0000

Data Index: 925952 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6631. Min Act: -0.0000

Data Index: 247016 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.7073. Min Act: -0.0000

Data Index: 661376 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.7123. Min Act: -0.0000

Data Index: 603218 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1164285 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1223931 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1231081 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6472. Min Act: -0.0000

Data Index: 536899 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6389. Min Act: -0.0000

Data Index: 829810 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6089. Min Act: -0.0000

Data Index: 162458 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6408. Min Act: -0.0000

Data Index: 835500 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.7300. Min Act: -0.0000

Data Index: 703402 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1121764 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5919. Min Act: -0.0000

Data Index: 371195 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6042. Min Act: -0.0000

Data Index: 310718 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5881. Min Act: -0.0000

Data Index: 842146 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5603. Min Act: -0.0000

Data Index: 95832 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5603. Min Act: -0.0000

Data Index: 933488 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1316493 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5659. Min Act: -0.0000

Data Index: 260375 (C4 (Web Text))

Max Activating Token Index: 200