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

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

Neuron 4435 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.2718. Min Act: -0.0000

Data Index: 917453 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1108062 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8685. Min Act: -0.0000

Data Index: 221497 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8430. Min Act: -0.0000

Data Index: 516161 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1299827 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.7975. Min Act: -0.0000

Data Index: 697587 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.7827. Min Act: -0.0000

Data Index: 641716 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.7474. Min Act: -0.0000

Data Index: 898171 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.7424. Min Act: -0.0000

Data Index: 239127 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.7333. Min Act: -0.0000

Data Index: 95883 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.7371. Min Act: -0.0000

Data Index: 292952 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1225955 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.7232. Min Act: -0.0000

Data Index: 778027 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.6791. Min Act: -0.0000

Data Index: 841763 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1279486 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.6931. Min Act: -0.0000

Data Index: 191565 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1012811 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.6481. Min Act: -0.0000

Data Index: 184110 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.6669. Min Act: -0.0000

Data Index: 36727 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1121277 (C4 (Web Text))

Max Activating Token Index: 89