Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1141 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.7442. Min Act: -0.0003

Data Index: 705744 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.8468. Min Act: -0.0003

Data Index: 981165 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.7219. Min Act: -0.0003

Data Index: 386659 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6716. Min Act: -0.0003

Data Index: 1136257 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6309. Min Act: -0.0003

Data Index: 504536 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.7704. Min Act: -0.0003

Data Index: 228245 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.7567. Min Act: -0.0003

Data Index: 1173129 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6135. Min Act: -0.0003

Data Index: 825683 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6914. Min Act: -0.0003

Data Index: 946691 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5756. Min Act: -0.0003

Data Index: 61290 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6120. Min Act: -0.0003

Data Index: 1256355 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6547. Min Act: -0.0003

Data Index: 1244537 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6542. Min Act: -0.0003

Data Index: 850089 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6397. Min Act: -0.0003

Data Index: 87081 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5867. Min Act: -0.0003

Data Index: 1098355 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6507. Min Act: -0.0003

Data Index: 31089 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6212. Min Act: -0.0003

Data Index: 399203 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5292. Min Act: -0.0003

Data Index: 1181770 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.4969. Min Act: -0.0003

Data Index: 489604 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6246. Min Act: -0.0003

Data Index: 815225 (C4 (Web Text))

Max Activating Token Index: 232