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

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

Neuron 4087 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6634. Min Range: -2.6634

Max Act: 2.6634. Min Act: -0.0000

Data Index: 1182686 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 2.6634. Min Range: -2.6634

Max Act: 2.4021. Min Act: -0.0000

Data Index: 777016 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 2.6634. Min Range: -2.6634

Max Act: 2.2948. Min Act: -0.0000

Data Index: 50759 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 2.6634. Min Range: -2.6634

Max Act: 2.2519. Min Act: -0.0000

Data Index: 1048561 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 2.6634. Min Range: -2.6634

Max Act: 2.2410. Min Act: -0.0000

Data Index: 1122448 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 2.6634. Min Range: -2.6634

Max Act: 2.0732. Min Act: -0.0000

Data Index: 310609 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 2.6634. Min Range: -2.6634

Max Act: 1.9204. Min Act: -0.0000

Data Index: 463407 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 2.6634. Min Range: -2.6634

Max Act: 1.8631. Min Act: -0.0000

Data Index: 120647 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 2.6634. Min Range: -2.6634

Max Act: 1.7575. Min Act: -0.0000

Data Index: 875888 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 2.6634. Min Range: -2.6634

Max Act: 2.1011. Min Act: -0.0000

Data Index: 378325 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 2.6634. Min Range: -2.6634

Max Act: 1.6873. Min Act: -0.0000

Data Index: 492192 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 2.6634. Min Range: -2.6634

Max Act: 1.6536. Min Act: -0.0000

Data Index: 899125 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 2.6634. Min Range: -2.6634

Max Act: 1.6524. Min Act: -0.0000

Data Index: 489237 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 2.6634. Min Range: -2.6634

Max Act: 1.3663. Min Act: -0.0000

Data Index: 669838 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 2.6634. Min Range: -2.6634

Max Act: 1.5982. Min Act: -0.0000

Data Index: 198255 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 2.6634. Min Range: -2.6634

Max Act: 1.5066. Min Act: -0.0000

Data Index: 201953 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 2.6634. Min Range: -2.6634

Max Act: 1.5412. Min Act: -0.0000

Data Index: 167443 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 2.6634. Min Range: -2.6634

Max Act: 1.6066. Min Act: -0.0000

Data Index: 905760 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 2.6634. Min Range: -2.6634

Max Act: 1.5090. Min Act: -0.0000

Data Index: 365560 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 2.6634. Min Range: -2.6634

Max Act: 1.3319. Min Act: -0.0000

Data Index: 1229538 (C4 (Web Text))

Max Activating Token Index: 802