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

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

Neuron 2386 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1401103 (Python Code)

Max Activating Token Index: 678

Text #1

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4543. Min Act: -0.0000

Data Index: 541816 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1653860 (Python Code)

Max Activating Token Index: 774

Text #3

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4623. Min Act: -0.0000

Data Index: 755499 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1475808 (Python Code)

Max Activating Token Index: 803

Text #5

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4138. Min Act: 0.0000

Data Index: 1004547 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1647260 (Python Code)

Max Activating Token Index: 200

Text #7

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1459088 (Python Code)

Max Activating Token Index: 166

Text #8

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1387891 (Python Code)

Max Activating Token Index: 605

Text #9

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1323011 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1371187 (Python Code)

Max Activating Token Index: 364

Text #11

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3985. Min Act: -0.0000

Data Index: 1426673 (Python Code)

Max Activating Token Index: 266

Text #12

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1391153 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1589787 (Python Code)

Max Activating Token Index: 520

Text #14

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1379942 (Python Code)

Max Activating Token Index: 402

Text #15

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1330282 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1653525 (Python Code)

Max Activating Token Index: 732

Text #17

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1535673 (Python Code)

Max Activating Token Index: 989

Text #18

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1577778 (Python Code)

Max Activating Token Index: 364

Text #19

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1648924 (Python Code)

Max Activating Token Index: 121