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

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

Neuron 2223 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0570. Min Act: -0.0001

Data Index: 43573 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0490. Min Act: -0.0001

Data Index: 246169 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0463. Min Act: -0.0001

Data Index: 407372 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0472. Min Act: -0.0001

Data Index: 118030 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0489. Min Act: -0.0001

Data Index: 577078 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0449. Min Act: -0.0001

Data Index: 439327 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1333023 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0464. Min Act: -0.0001

Data Index: 601453 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0441. Min Act: -0.0001

Data Index: 385477 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0441. Min Act: -0.0001

Data Index: 673950 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0437. Min Act: -0.0001

Data Index: 454636 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0439. Min Act: -0.0001

Data Index: 818183 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0437. Min Act: -0.0001

Data Index: 971490 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1124951 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1247526 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0458. Min Act: -0.0001

Data Index: 636317 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0409. Min Act: -0.0001

Data Index: 848313 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0430. Min Act: -0.0001

Data Index: 824579 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1242318 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0388. Min Act: -0.0001

Data Index: 51482 (C4 (Web Text))

Max Activating Token Index: 873