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

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

Neuron 534 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1101. Min Range: -1.1101

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1529195 (Python Code)

Max Activating Token Index: 565

Text #1

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1621638 (Python Code)

Max Activating Token Index: 814

Text #2

Max Range: 1.1101. Min Range: -1.1101

Max Act: 1.1101. Min Act: -0.0000

Data Index: 1634654 (Python Code)

Max Activating Token Index: 867

Text #3

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.9370. Min Act: -0.0000

Data Index: 1534453 (Python Code)

Max Activating Token Index: 528

Text #4

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.8897. Min Act: -0.0000

Data Index: 1428276 (Python Code)

Max Activating Token Index: 685

Text #5

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1535922 (Python Code)

Max Activating Token Index: 300

Text #6

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1611011 (Python Code)

Max Activating Token Index: 374

Text #7

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1512743 (Python Code)

Max Activating Token Index: 838

Text #8

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.8951. Min Act: -0.0000

Data Index: 1580172 (Python Code)

Max Activating Token Index: 857

Text #9

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1595322 (Python Code)

Max Activating Token Index: 928

Text #10

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1503488 (Python Code)

Max Activating Token Index: 925

Text #11

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.8498. Min Act: -0.0000

Data Index: 1364758 (Python Code)

Max Activating Token Index: 823

Text #12

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1397359 (Python Code)

Max Activating Token Index: 405

Text #13

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1567748 (Python Code)

Max Activating Token Index: 903

Text #14

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1538919 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1602387 (Python Code)

Max Activating Token Index: 479

Text #16

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1407612 (Python Code)

Max Activating Token Index: 322

Text #17

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1614616 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1552383 (Python Code)

Max Activating Token Index: 351

Text #19

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1575314 (Python Code)

Max Activating Token Index: 188