Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1186 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.9558. Min Act: -0.0001

Data Index: 1625576 (Python Code)

Max Activating Token Index: 242

Text #1

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.9350. Min Act: -0.0001

Data Index: 264793 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.8583. Min Act: -0.0001

Data Index: 1246054 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7592. Min Act: -0.0001

Data Index: 1548694 (Python Code)

Max Activating Token Index: 485

Text #4

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.8587. Min Act: -0.0001

Data Index: 660963 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.8721. Min Act: -0.0001

Data Index: 785643 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7935. Min Act: -0.0001

Data Index: 418479 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7801. Min Act: -0.0001

Data Index: 1030849 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7452. Min Act: -0.0001

Data Index: 628324 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7666. Min Act: -0.0001

Data Index: 224908 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7071. Min Act: -0.0001

Data Index: 817360 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7529. Min Act: -0.0001

Data Index: 871948 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7025. Min Act: -0.0001

Data Index: 821877 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7265. Min Act: -0.0001

Data Index: 1170446 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7138. Min Act: -0.0001

Data Index: 891977 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7575. Min Act: -0.0001

Data Index: 1178546 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7411. Min Act: -0.0001

Data Index: 947081 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6433. Min Act: -0.0001

Data Index: 823618 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6596. Min Act: -0.0001

Data Index: 550357 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7039. Min Act: -0.0001

Data Index: 1603562 (Python Code)

Max Activating Token Index: 248