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

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

Neuron 2242 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: 0.4736. Min Range: -0.4736

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1494356 (Python Code)

Max Activating Token Index: 68

Text #1

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1586936 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1384548 (Python Code)

Max Activating Token Index: 123

Text #3

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4505. Min Act: -0.0000

Data Index: 919260 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1374207 (Python Code)

Max Activating Token Index: 402

Text #5

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1556371 (Python Code)

Max Activating Token Index: 986

Text #6

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3845. Min Act: -0.0000

Data Index: 269542 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3795. Min Act: -0.0000

Data Index: 193462 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1482707 (Python Code)

Max Activating Token Index: 153

Text #9

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1344791 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3640. Min Act: -0.0000

Data Index: 900399 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1546583 (Python Code)

Max Activating Token Index: 387

Text #12

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1522002 (Python Code)

Max Activating Token Index: 328

Text #13

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3731. Min Act: -0.0000

Data Index: 195307 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1215488 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3351. Min Act: -0.0000

Data Index: 594454 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1382884 (Python Code)

Max Activating Token Index: 724

Text #17

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1162056 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3589. Min Act: -0.0000

Data Index: 1119720 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3402. Min Act: -0.0000

Data Index: 953176 (C4 (Web Text))

Max Activating Token Index: 783