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

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

Neuron 698 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: 0.6789. Min Range: -0.6789

Max Act: 0.6789. Min Act: -0.0001

Data Index: 1384288 (Python Code)

Max Activating Token Index: 415

Text #1

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4886. Min Act: -0.0001

Data Index: 1436908 (Python Code)

Max Activating Token Index: 50

Text #2

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4502. Min Act: -0.0001

Data Index: 1068208 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3761. Min Act: -0.0001

Data Index: 1480553 (Python Code)

Max Activating Token Index: 358

Text #4

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3993. Min Act: -0.0001

Data Index: 814984 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3847. Min Act: -0.0001

Data Index: 15458 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3946. Min Act: -0.0001

Data Index: 657610 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3831. Min Act: -0.0001

Data Index: 1492277 (Python Code)

Max Activating Token Index: 99

Text #8

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1326097 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1076195 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3638. Min Act: -0.0001

Data Index: 570014 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3872. Min Act: -0.0001

Data Index: 717878 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3735. Min Act: -0.0000

Data Index: 993900 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3785. Min Act: -0.0001

Data Index: 483240 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3498. Min Act: -0.0000

Data Index: 957659 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3534. Min Act: -0.0001

Data Index: 478582 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3663. Min Act: -0.0001

Data Index: 189173 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3607. Min Act: -0.0001

Data Index: 665735 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3468. Min Act: -0.0001

Data Index: 68786 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.3377. Min Act: -0.0001

Data Index: 774067 (C4 (Web Text))

Max Activating Token Index: 863