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

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

Neuron 912 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: 0.0593. Min Range: -0.0593

Max Act: 0.0593. Min Act: -0.0003

Data Index: 89566 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0552. Min Act: -0.0003

Data Index: 414433 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0519. Min Act: -0.0003

Data Index: 421843 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0467. Min Act: -0.0003

Data Index: 566745 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0534. Min Act: -0.0003

Data Index: 384142 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0534. Min Act: -0.0003

Data Index: 167901 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0533. Min Act: -0.0003

Data Index: 864845 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0427. Min Act: -0.0003

Data Index: 380660 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0426. Min Act: -0.0003

Data Index: 1225456 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0426. Min Act: -0.0003

Data Index: 1093941 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1302543 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1268884 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0413. Min Act: -0.0003

Data Index: 1291289 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0427. Min Act: -0.0003

Data Index: 173901 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0470. Min Act: -0.0003

Data Index: 654108 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0432. Min Act: -0.0003

Data Index: 61189 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0426. Min Act: -0.0003

Data Index: 125382 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0411. Min Act: -0.0003

Data Index: 1155928 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0450. Min Act: -0.0003

Data Index: 671630 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0448. Min Act: -0.0003

Data Index: 500070 (C4 (Web Text))

Max Activating Token Index: 177