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

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

Neuron 2271 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3466. Min Range: -2.3466

Max Act: 2.3466. Min Act: -0.0000

Data Index: 73192 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 2.3466. Min Range: -2.3466

Max Act: 2.0730. Min Act: -0.0000

Data Index: 1138012 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.8109. Min Act: -0.0000

Data Index: 1486610 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.7967. Min Act: -0.0000

Data Index: 521430 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.6036. Min Act: -0.0000

Data Index: 116858 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.7037. Min Act: -0.0000

Data Index: 207817 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.6610. Min Act: -0.0000

Data Index: 631585 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.3992. Min Act: -0.0000

Data Index: 121329 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.6272. Min Act: -0.0000

Data Index: 811733 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.5224. Min Act: -0.0000

Data Index: 1615293 (Python Code)

Max Activating Token Index: 64

Text #10

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.4394. Min Act: -0.0000

Data Index: 1626719 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.3643. Min Act: -0.0000

Data Index: 1620208 (Python Code)

Max Activating Token Index: 991

Text #12

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.3648. Min Act: -0.0000

Data Index: 923963 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.3648. Min Act: -0.0000

Data Index: 442279 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.3648. Min Act: -0.0000

Data Index: 133179 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.3648. Min Act: -0.0000

Data Index: 861214 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.3648. Min Act: -0.0000

Data Index: 993000 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.3648. Min Act: -0.0000

Data Index: 48561 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.1563. Min Act: -0.0000

Data Index: 810533 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.1909. Min Act: -0.0000

Data Index: 574784 (C4 (Web Text))

Max Activating Token Index: 927