Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2537 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0526. Min Act: -0.0003

Data Index: 933019 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1332271 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0479. Min Act: -0.0003

Data Index: 795012 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0569. Min Act: -0.0003

Data Index: 225535 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0481. Min Act: -0.0003

Data Index: 546215 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0460. Min Act: -0.0003

Data Index: 1265525 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0401. Min Act: -0.0003

Data Index: 857638 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0427. Min Act: -0.0003

Data Index: 59483 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0442. Min Act: -0.0003

Data Index: 91435 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0442. Min Act: -0.0003

Data Index: 275420 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0438. Min Act: -0.0003

Data Index: 260288 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0407. Min Act: -0.0003

Data Index: 561469 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1076933 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0468. Min Act: -0.0003

Data Index: 971197 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0345. Min Act: -0.0003

Data Index: 879013 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0408. Min Act: -0.0003

Data Index: 552793 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1236563 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0407. Min Act: -0.0003

Data Index: 471853 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0418. Min Act: -0.0003

Data Index: 700225 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0372. Min Act: -0.0003

Data Index: 1333930 (C4 (Web Text))

Max Activating Token Index: 691