Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 191 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0522. Min Act: -0.0001

Data Index: 907473 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0001

Data Index: 763946 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0500. Min Act: -0.0001

Data Index: 152839 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1106424 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1012669 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0454. Min Act: -0.0001

Data Index: 1233336 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0416. Min Act: -0.0001

Data Index: 647464 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0373. Min Act: -0.0001

Data Index: 1348640 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1173929 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0348. Min Act: -0.0001

Data Index: 602716 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0367. Min Act: -0.0001

Data Index: 100864 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0367. Min Act: -0.0001

Data Index: 282040 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0369. Min Act: -0.0001

Data Index: 982535 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0379. Min Act: -0.0001

Data Index: 870027 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0369. Min Act: -0.0001

Data Index: 838352 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0346. Min Act: -0.0001

Data Index: 513644 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0374. Min Act: -0.0001

Data Index: 207268 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0354. Min Act: -0.0001

Data Index: 982099 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0321. Min Act: -0.0001

Data Index: 840727 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0336. Min Act: -0.0001

Data Index: 602555 (C4 (Web Text))

Max Activating Token Index: 896