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

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

Neuron 5003 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.6932. Min Act: -0.0000

Data Index: 1468004 (Python Code)

Max Activating Token Index: 771

Text #1

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.5362. Min Act: -0.0000

Data Index: 1532528 (Python Code)

Max Activating Token Index: 542

Text #2

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.2194. Min Act: -0.0000

Data Index: 1470895 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1547597 (Python Code)

Max Activating Token Index: 872

Text #4

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1984. Min Act: -0.0000

Data Index: 1650754 (Python Code)

Max Activating Token Index: 229

Text #5

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1728. Min Act: -0.0000

Data Index: 1610066 (Python Code)

Max Activating Token Index: 566

Text #6

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1563850 (Python Code)

Max Activating Token Index: 525

Text #7

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.0722. Min Act: -0.0000

Data Index: 1510207 (Python Code)

Max Activating Token Index: 495

Text #8

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1525010 (Python Code)

Max Activating Token Index: 245

Text #9

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1395202 (Python Code)

Max Activating Token Index: 432

Text #10

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1735. Min Act: -0.0000

Data Index: 1374248 (Python Code)

Max Activating Token Index: 963

Text #11

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.0890. Min Act: -0.0000

Data Index: 1394414 (Python Code)

Max Activating Token Index: 951

Text #12

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1092. Min Act: -0.0000

Data Index: 1589678 (Python Code)

Max Activating Token Index: 92

Text #13

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.0053. Min Act: -0.0000

Data Index: 1567518 (Python Code)

Max Activating Token Index: 712

Text #14

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.0318. Min Act: -0.0000

Data Index: 1555109 (Python Code)

Max Activating Token Index: 377

Text #15

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1237. Min Act: -0.0000

Data Index: 1571802 (Python Code)

Max Activating Token Index: 121

Text #16

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.0583. Min Act: -0.0000

Data Index: 1375058 (Python Code)

Max Activating Token Index: 153

Text #17

Max Range: 1.6932. Min Range: -1.6932

Max Act: 0.9699. Min Act: -0.0001

Data Index: 1490387 (Python Code)

Max Activating Token Index: 880

Text #18

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.0783. Min Act: -0.0000

Data Index: 1511948 (Python Code)

Max Activating Token Index: 398

Text #19

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1372972 (Python Code)

Max Activating Token Index: 180