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

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

Neuron 76 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1200. Min Act: -0.0001

Data Index: 140556 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0985. Min Act: -0.0000

Data Index: 453843 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0957. Min Act: -0.0000

Data Index: 858985 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0856. Min Act: -0.0000

Data Index: 29705 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0786. Min Act: -0.0000

Data Index: 741389 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1476698 (Python Code)

Max Activating Token Index: 507

Text #6

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0654. Min Act: -0.0000

Data Index: 3543 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1001204 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1588310 (Python Code)

Max Activating Token Index: 395

Text #9

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0620. Min Act: -0.0000

Data Index: 1185785 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0661. Min Act: -0.0000

Data Index: 239230 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0431. Min Act: -0.0000

Data Index: 1460040 (Python Code)

Max Activating Token Index: 354

Text #12

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0632. Min Act: -0.0000

Data Index: 1292596 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0574. Min Act: -0.0000

Data Index: 595934 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1233221 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0620. Min Act: -0.0000

Data Index: 647439 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0579. Min Act: -0.0000

Data Index: 277702 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0622. Min Act: -0.0000

Data Index: 1024944 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1288444 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0630. Min Act: -0.0000

Data Index: 205520 (C4 (Web Text))

Max Activating Token Index: 879