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

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

Neuron 304 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: 0.1694. Min Range: -0.1694

Max Act: 0.1694. Min Act: -0.0003

Data Index: 1230752 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1672. Min Act: -0.0003

Data Index: 138288 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1516. Min Act: -0.0003

Data Index: 1036213 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1395. Min Act: -0.0003

Data Index: 226990 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1290. Min Act: -0.0003

Data Index: 817866 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1547. Min Act: -0.0003

Data Index: 1325335 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1387. Min Act: -0.0003

Data Index: 824047 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1513. Min Act: -0.0003

Data Index: 819245 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1459. Min Act: -0.0003

Data Index: 157831 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1506. Min Act: -0.0003

Data Index: 1225340 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1451. Min Act: -0.0003

Data Index: 1328330 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1395. Min Act: -0.0003

Data Index: 641940 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1451. Min Act: -0.0003

Data Index: 997553 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1448. Min Act: -0.0003

Data Index: 542308 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1477. Min Act: -0.0003

Data Index: 994018 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1323. Min Act: -0.0003

Data Index: 442160 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1319. Min Act: -0.0003

Data Index: 921634 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1426. Min Act: -0.0003

Data Index: 584385 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1459. Min Act: -0.0003

Data Index: 239793 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1386. Min Act: -0.0003

Data Index: 482762 (C4 (Web Text))

Max Activating Token Index: 430