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

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

Neuron 2610 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.7315. Min Act: -0.0001

Data Index: 704756 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6238. Min Act: -0.0000

Data Index: 873146 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6407. Min Act: -0.0001

Data Index: 751349 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.3310. Min Act: -0.0001

Data Index: 386881 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.4287. Min Act: -0.0000

Data Index: 1031867 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.2799. Min Act: -0.0000

Data Index: 15742 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.2253. Min Act: -0.0000

Data Index: 495847 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.2662. Min Act: -0.0000

Data Index: 998409 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.2365. Min Act: -0.0001

Data Index: 987720 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.2761. Min Act: -0.0000

Data Index: 1062308 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.1595. Min Act: -0.0001

Data Index: 209112 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.2488. Min Act: -0.0001

Data Index: 389681 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.1511. Min Act: -0.0001

Data Index: 631663 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.1424. Min Act: -0.0001

Data Index: 1258313 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.0941. Min Act: -0.0001

Data Index: 59295 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.1915. Min Act: -0.0001

Data Index: 869660 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.1783. Min Act: -0.0000

Data Index: 962530 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.1762. Min Act: -0.0000

Data Index: 1290923 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.2395. Min Act: -0.0000

Data Index: 1257427 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.1434. Min Act: -0.0001

Data Index: 554227 (C4 (Web Text))

Max Activating Token Index: 461