Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 985 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0516. Min Act: -0.0002

Data Index: 199895 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0514. Min Act: -0.0002

Data Index: 328308 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0482. Min Act: -0.0002

Data Index: 535932 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1142254 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1542462 (Python Code)

Max Activating Token Index: 591

Text #5

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0470. Min Act: -0.0002

Data Index: 908469 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0456. Min Act: -0.0002

Data Index: 960418 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0466. Min Act: -0.0002

Data Index: 52744 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0466. Min Act: -0.0002

Data Index: 756540 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1646637 (Python Code)

Max Activating Token Index: 645

Text #10

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0451. Min Act: -0.0002

Data Index: 352739 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1192021 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1206023 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0448. Min Act: -0.0001

Data Index: 492880 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1619948 (Python Code)

Max Activating Token Index: 501

Text #15

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0440. Min Act: -0.0002

Data Index: 208535 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0438. Min Act: -0.0002

Data Index: 670706 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1217720 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0431. Min Act: -0.0002

Data Index: 164429 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0429. Min Act: -0.0002

Data Index: 508656 (C4 (Web Text))

Max Activating Token Index: 642