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

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

Neuron 1343 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4671. Min Act: -0.0000

Data Index: 647714 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4785. Min Act: -0.0000

Data Index: 919913 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1104160 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4239. Min Act: -0.0000

Data Index: 886071 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4007. Min Act: -0.0000

Data Index: 958820 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1273725 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1516995 (Python Code)

Max Activating Token Index: 414

Text #7

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1478997 (Python Code)

Max Activating Token Index: 358

Text #8

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4083. Min Act: -0.0000

Data Index: 104210 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3982. Min Act: -0.0000

Data Index: 576168 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3964. Min Act: -0.0000

Data Index: 42870 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3674. Min Act: -0.0000

Data Index: 75481 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1271233 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1439911 (Python Code)

Max Activating Token Index: 216

Text #14

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3810. Min Act: -0.0000

Data Index: 934454 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1452973 (Python Code)

Max Activating Token Index: 480

Text #16

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1186693 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1533356 (Python Code)

Max Activating Token Index: 744

Text #18

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1653091 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3814. Min Act: -0.0000

Data Index: 895596 (C4 (Web Text))

Max Activating Token Index: 798