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

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

Neuron 3251 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0002

Data Index: 579887 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0659. Min Act: -0.0002

Data Index: 821945 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1348063 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0557. Min Act: -0.0002

Data Index: 597744 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0545. Min Act: -0.0002

Data Index: 503069 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1267971 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0499. Min Act: -0.0002

Data Index: 381473 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0494. Min Act: -0.0002

Data Index: 778710 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0492. Min Act: -0.0002

Data Index: 884215 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0491. Min Act: -0.0002

Data Index: 42286 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1307698 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0491. Min Act: -0.0002

Data Index: 275022 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0479. Min Act: -0.0002

Data Index: 109091 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1042631 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0464. Min Act: -0.0002

Data Index: 317010 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0456. Min Act: -0.0002

Data Index: 905692 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1358343 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1057134 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0440. Min Act: -0.0002

Data Index: 489977 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0439. Min Act: -0.0002

Data Index: 801076 (C4 (Web Text))

Max Activating Token Index: 80