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

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

Neuron 2570 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.9335. Min Act: -0.0001

Data Index: 812808 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.4339. Min Act: -0.0001

Data Index: 531168 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.1418. Min Act: -0.0001

Data Index: 886665 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.1189. Min Act: -0.0000

Data Index: 1471093 (Python Code)

Max Activating Token Index: 831

Text #4

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.1403. Min Act: -0.0001

Data Index: 1460664 (Python Code)

Max Activating Token Index: 181

Text #5

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.2052. Min Act: -0.0001

Data Index: 9186 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.1697. Min Act: -0.0001

Data Index: 627880 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1438521 (Python Code)

Max Activating Token Index: 562

Text #8

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.0847. Min Act: -0.0000

Data Index: 1573085 (Python Code)

Max Activating Token Index: 995

Text #9

Max Range: 1.9335. Min Range: -1.9335

Max Act: 0.9555. Min Act: -0.0001

Data Index: 832582 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.0683. Min Act: -0.0001

Data Index: 1645033 (Python Code)

Max Activating Token Index: 888

Text #11

Max Range: 1.9335. Min Range: -1.9335

Max Act: 0.9930. Min Act: -0.0001

Data Index: 1393107 (Python Code)

Max Activating Token Index: 168

Text #12

Max Range: 1.9335. Min Range: -1.9335

Max Act: 0.9407. Min Act: -0.0001

Data Index: 1493005 (Python Code)

Max Activating Token Index: 954

Text #13

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.0235. Min Act: -0.0001

Data Index: 1527952 (Python Code)

Max Activating Token Index: 619

Text #14

Max Range: 1.9335. Min Range: -1.9335

Max Act: 0.9772. Min Act: -0.0001

Data Index: 1555342 (Python Code)

Max Activating Token Index: 225

Text #15

Max Range: 1.9335. Min Range: -1.9335

Max Act: 0.9630. Min Act: -0.0001

Data Index: 1655283 (Python Code)

Max Activating Token Index: 142

Text #16

Max Range: 1.9335. Min Range: -1.9335

Max Act: 0.9985. Min Act: -0.0001

Data Index: 59385 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 1.9335. Min Range: -1.9335

Max Act: 0.9696. Min Act: -0.0001

Data Index: 609924 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 1.9335. Min Range: -1.9335

Max Act: 0.9415. Min Act: -0.0001

Data Index: 1535931 (Python Code)

Max Activating Token Index: 472

Text #19

Max Range: 1.9335. Min Range: -1.9335

Max Act: 0.8910. Min Act: -0.0000

Data Index: 683291 (C4 (Web Text))

Max Activating Token Index: 403