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

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

Neuron 1635 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1449379 (Python Code)

Max Activating Token Index: 393

Text #1

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5039. Min Act: -0.0001

Data Index: 1460564 (Python Code)

Max Activating Token Index: 1013

Text #2

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5271. Min Act: -0.0001

Data Index: 1477054 (Python Code)

Max Activating Token Index: 1007

Text #3

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4826. Min Act: -0.0001

Data Index: 1477459 (Python Code)

Max Activating Token Index: 836

Text #4

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5030. Min Act: -0.0001

Data Index: 1461634 (Python Code)

Max Activating Token Index: 576

Text #5

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5333. Min Act: -0.0001

Data Index: 1450498 (Python Code)

Max Activating Token Index: 1006

Text #6

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5111. Min Act: -0.0001

Data Index: 1552991 (Python Code)

Max Activating Token Index: 524

Text #7

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4821. Min Act: -0.0001

Data Index: 1518826 (Python Code)

Max Activating Token Index: 207

Text #8

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4637. Min Act: -0.0001

Data Index: 1435347 (Python Code)

Max Activating Token Index: 921

Text #9

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4951. Min Act: -0.0001

Data Index: 1564025 (Python Code)

Max Activating Token Index: 403

Text #10

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4752. Min Act: -0.0001

Data Index: 1342493 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4737. Min Act: -0.0001

Data Index: 498426 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4577. Min Act: -0.0001

Data Index: 1369532 (Python Code)

Max Activating Token Index: 678

Text #13

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4862. Min Act: -0.0001

Data Index: 1645913 (Python Code)

Max Activating Token Index: 915

Text #14

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4514. Min Act: -0.0001

Data Index: 647961 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4840. Min Act: -0.0001

Data Index: 1360255 (Python Code)

Max Activating Token Index: 205

Text #16

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4646. Min Act: -0.0001

Data Index: 327563 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4626. Min Act: -0.0001

Data Index: 1655752 (Python Code)

Max Activating Token Index: 883

Text #18

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4623. Min Act: -0.0001

Data Index: 416989 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4614. Min Act: -0.0001

Data Index: 1465751 (Python Code)

Max Activating Token Index: 13