Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 516 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0001

Data Index: 26262 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1324250 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0428. Min Act: -0.0001

Data Index: 204744 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1331564 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0399. Min Act: -0.0001

Data Index: 809225 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0409. Min Act: -0.0001

Data Index: 1468253 (Python Code)

Max Activating Token Index: 452

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0420. Min Act: -0.0001

Data Index: 193847 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0438. Min Act: -0.0001

Data Index: 624536 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0413. Min Act: -0.0001

Data Index: 402645 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0416. Min Act: -0.0001

Data Index: 874308 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1054066 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0400. Min Act: -0.0001

Data Index: 675866 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0416. Min Act: -0.0001

Data Index: 462361 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0379. Min Act: -0.0001

Data Index: 379324 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1274206 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1350052 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0393. Min Act: -0.0001

Data Index: 247374 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0377. Min Act: -0.0001

Data Index: 290894 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0400. Min Act: -0.0001

Data Index: 614124 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0378. Min Act: -0.0001

Data Index: 465882 (C4 (Web Text))

Max Activating Token Index: 156