Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3303 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1897. Min Act: -0.0002

Data Index: 883161 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1541. Min Act: -0.0002

Data Index: 310470 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1619. Min Act: -0.0002

Data Index: 503053 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1604. Min Act: -0.0002

Data Index: 1055078 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1599. Min Act: -0.0002

Data Index: 679371 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1488. Min Act: -0.0002

Data Index: 1191795 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1360. Min Act: -0.0002

Data Index: 437163 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1514. Min Act: -0.0002

Data Index: 1217834 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1454. Min Act: -0.0002

Data Index: 497392 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1443. Min Act: -0.0002

Data Index: 339027 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1389. Min Act: -0.0002

Data Index: 576713 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1530. Min Act: -0.0002

Data Index: 1212051 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1577. Min Act: -0.0002

Data Index: 1157412 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1507. Min Act: -0.0002

Data Index: 1117512 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1459. Min Act: -0.0002

Data Index: 403528 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1411. Min Act: -0.0002

Data Index: 1288969 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1441. Min Act: -0.0002

Data Index: 809115 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1374. Min Act: -0.0002

Data Index: 179042 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1435. Min Act: -0.0002

Data Index: 1116688 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1447. Min Act: -0.0002

Data Index: 917015 (C4 (Web Text))

Max Activating Token Index: 16