Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3421 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.3113. Min Act: -0.0000

Data Index: 1381135 (Python Code)

Max Activating Token Index: 700

Text #1

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.2970. Min Act: -0.0001

Data Index: 1632915 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1402743 (Python Code)

Max Activating Token Index: 806

Text #3

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.1365. Min Act: -0.0001

Data Index: 1586871 (Python Code)

Max Activating Token Index: 531

Text #4

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.1407. Min Act: -0.0000

Data Index: 1532560 (Python Code)

Max Activating Token Index: 1000

Text #5

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.1180. Min Act: -0.0001

Data Index: 1574789 (Python Code)

Max Activating Token Index: 435

Text #6

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.0502. Min Act: -0.0001

Data Index: 1570470 (Python Code)

Max Activating Token Index: 776

Text #7

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.0396. Min Act: -0.0001

Data Index: 1483564 (Python Code)

Max Activating Token Index: 306

Text #8

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.0585. Min Act: -0.0001

Data Index: 1494972 (Python Code)

Max Activating Token Index: 939

Text #9

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.0805. Min Act: -0.0001

Data Index: 1518782 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.0853. Min Act: -0.0000

Data Index: 1493845 (Python Code)

Max Activating Token Index: 800

Text #11

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.0334. Min Act: -0.0000

Data Index: 1458175 (Python Code)

Max Activating Token Index: 465

Text #12

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.0404. Min Act: -0.0001

Data Index: 1474480 (Python Code)

Max Activating Token Index: 425

Text #13

Max Range: 1.3113. Min Range: -1.3113

Max Act: 0.9653. Min Act: -0.0001

Data Index: 1442577 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.0094. Min Act: -0.0000

Data Index: 1339096 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 1.3113. Min Range: -1.3113

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1511608 (Python Code)

Max Activating Token Index: 524

Text #16

Max Range: 1.3113. Min Range: -1.3113

Max Act: 0.9399. Min Act: -0.0001

Data Index: 1440376 (Python Code)

Max Activating Token Index: 867

Text #17

Max Range: 1.3113. Min Range: -1.3113

Max Act: 0.8967. Min Act: -0.0001

Data Index: 1528543 (Python Code)

Max Activating Token Index: 556

Text #18

Max Range: 1.3113. Min Range: -1.3113

Max Act: 0.9301. Min Act: -0.0001

Data Index: 1611424 (Python Code)

Max Activating Token Index: 737

Text #19

Max Range: 1.3113. Min Range: -1.3113

Max Act: 1.0013. Min Act: -0.0000

Data Index: 1442816 (Python Code)

Max Activating Token Index: 707