Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1450 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.6393. Min Act: -0.0001

Data Index: 53846 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.5767. Min Act: -0.0001

Data Index: 360546 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.5482. Min Act: -0.0000

Data Index: 743278 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.5582. Min Act: -0.0001

Data Index: 638650 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.5758. Min Act: -0.0000

Data Index: 299496 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.5650. Min Act: -0.0000

Data Index: 103431 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.5096. Min Act: 0.0000

Data Index: 148811 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.5512. Min Act: -0.0000

Data Index: 622994 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.5540. Min Act: -0.0001

Data Index: 1401513 (Python Code)

Max Activating Token Index: 622

Text #9

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.5107. Min Act: -0.0001

Data Index: 803851 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1347106 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.4895. Min Act: -0.0000

Data Index: 811167 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.5022. Min Act: -0.0000

Data Index: 370871 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.4956. Min Act: -0.0000

Data Index: 213816 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.4863. Min Act: -0.0001

Data Index: 98730 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.4954. Min Act: -0.0000

Data Index: 167109 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.4948. Min Act: -0.0001

Data Index: 321097 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.5022. Min Act: -0.0001

Data Index: 436028 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.4346. Min Act: -0.0001

Data Index: 122767 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.6393. Min Range: -0.6393

Max Act: 0.4661. Min Act: -0.0001

Data Index: 1090553 (C4 (Web Text))

Max Activating Token Index: 279