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

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

Neuron 5493 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: 3.7777. Min Range: -3.7777

Max Act: 3.7777. Min Act: -0.0000

Data Index: 1357580 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.7501. Min Act: -0.0000

Data Index: 445689 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.6707. Min Act: -0.0000

Data Index: 990232 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.0167. Min Act: -0.0000

Data Index: 459492 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.3036. Min Act: -0.0000

Data Index: 1065452 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 3.7777. Min Range: -3.7777

Max Act: 2.8468. Min Act: -0.0000

Data Index: 1336076 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.2459. Min Act: -0.0000

Data Index: 1043407 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.0964. Min Act: -0.0000

Data Index: 11294 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.2257. Min Act: -0.0000

Data Index: 1033063 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.0805. Min Act: -0.0000

Data Index: 255414 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.0383. Min Act: -0.0000

Data Index: 191339 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 3.7777. Min Range: -3.7777

Max Act: 2.8570. Min Act: -0.0000

Data Index: 668001 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.0093. Min Act: -0.0000

Data Index: 376712 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 3.7777. Min Range: -3.7777

Max Act: 2.9888. Min Act: -0.0000

Data Index: 836134 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.0926. Min Act: -0.0000

Data Index: 129481 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 3.7777. Min Range: -3.7777

Max Act: 2.9599. Min Act: -0.0000

Data Index: 885509 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 3.7777. Min Range: -3.7777

Max Act: 2.9362. Min Act: -0.0000

Data Index: 78885 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.0707. Min Act: -0.0000

Data Index: 558400 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 3.7777. Min Range: -3.7777

Max Act: 2.9310. Min Act: -0.0000

Data Index: 1277769 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 3.7777. Min Range: -3.7777

Max Act: 3.0403. Min Act: -0.0000

Data Index: 626206 (C4 (Web Text))

Max Activating Token Index: 891