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

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

Neuron 74 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1600870 (Python Code)

Max Activating Token Index: 958

Text #1

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1596270 (Python Code)

Max Activating Token Index: 852

Text #2

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1390384 (Python Code)

Max Activating Token Index: 510

Text #3

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1010. Min Act: -0.0000

Data Index: 579882 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1386270 (Python Code)

Max Activating Token Index: 999

Text #5

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0915. Min Act: -0.0000

Data Index: 960058 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0870. Min Act: -0.0000

Data Index: 1470947 (Python Code)

Max Activating Token Index: 850

Text #7

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0891. Min Act: -0.0000

Data Index: 124845 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0880. Min Act: 0.0000

Data Index: 1494988 (Python Code)

Max Activating Token Index: 157

Text #9

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0877. Min Act: -0.0000

Data Index: 946653 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1438400 (Python Code)

Max Activating Token Index: 221

Text #11

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0905. Min Act: -0.0000

Data Index: 838322 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0869. Min Act: -0.0000

Data Index: 184577 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1583541 (Python Code)

Max Activating Token Index: 260

Text #14

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0826. Min Act: -0.0001

Data Index: 1497784 (Python Code)

Max Activating Token Index: 243

Text #15

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1571611 (Python Code)

Max Activating Token Index: 474

Text #16

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0819. Min Act: -0.0000

Data Index: 522387 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0841. Min Act: -0.0001

Data Index: 3161 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1575680 (Python Code)

Max Activating Token Index: 374

Text #19

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0811. Min Act: -0.0001

Data Index: 462364 (C4 (Web Text))

Max Activating Token Index: 559