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

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

Neuron 1989 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: 0.1994. Min Range: -0.1994

Max Act: 0.1994. Min Act: -0.0001

Data Index: 522931 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1639534 (Python Code)

Max Activating Token Index: 454

Text #2

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1472432 (Python Code)

Max Activating Token Index: 776

Text #3

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1491690 (Python Code)

Max Activating Token Index: 615

Text #4

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1364. Min Act: -0.0001

Data Index: 1567437 (Python Code)

Max Activating Token Index: 350

Text #5

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1492. Min Act: -0.0001

Data Index: 1581787 (Python Code)

Max Activating Token Index: 659

Text #6

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1796. Min Act: -0.0001

Data Index: 1379005 (Python Code)

Max Activating Token Index: 354

Text #7

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1408. Min Act: -0.0001

Data Index: 1560084 (Python Code)

Max Activating Token Index: 190

Text #8

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1558704 (Python Code)

Max Activating Token Index: 198

Text #9

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1611614 (Python Code)

Max Activating Token Index: 249

Text #10

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1464660 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1280. Min Act: -0.0001

Data Index: 1373759 (Python Code)

Max Activating Token Index: 279

Text #12

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1405. Min Act: -0.0001

Data Index: 1414579 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1422558 (Python Code)

Max Activating Token Index: 905

Text #14

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1498. Min Act: -0.0001

Data Index: 1392891 (Python Code)

Max Activating Token Index: 436

Text #15

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1378567 (Python Code)

Max Activating Token Index: 430

Text #16

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1439. Min Act: -0.0001

Data Index: 808347 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1342. Min Act: -0.0001

Data Index: 1642270 (Python Code)

Max Activating Token Index: 526

Text #18

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1602067 (Python Code)

Max Activating Token Index: 640

Text #19

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1586342 (Python Code)

Max Activating Token Index: 220