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

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

Neuron 2167 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.3049. Min Act: -0.0001

Data Index: 1067539 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1067819 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.3014. Min Act: -0.0001

Data Index: 275929 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2829. Min Act: -0.0000

Data Index: 479159 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2740. Min Act: -0.0000

Data Index: 609519 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1346806 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2504. Min Act: -0.0001

Data Index: 217132 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2577. Min Act: -0.0001

Data Index: 316020 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2556. Min Act: -0.0001

Data Index: 744521 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2426. Min Act: -0.0001

Data Index: 546697 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2496. Min Act: -0.0001

Data Index: 1235465 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2502. Min Act: -0.0000

Data Index: 515096 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2487. Min Act: -0.0000

Data Index: 284266 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2382. Min Act: -0.0000

Data Index: 351607 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2550. Min Act: -0.0000

Data Index: 925385 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2344. Min Act: -0.0001

Data Index: 921232 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2416. Min Act: -0.0000

Data Index: 187305 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2409. Min Act: -0.0000

Data Index: 718175 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2407. Min Act: -0.0001

Data Index: 745851 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2406. Min Act: -0.0000

Data Index: 94878 (C4 (Web Text))

Max Activating Token Index: 1018