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

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

Neuron 3701 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: 4.4607. Min Range: -4.4607

Max Act: 4.4607. Min Act: -0.0000

Data Index: 853541 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 4.4607. Min Range: -4.4607

Max Act: 4.2712. Min Act: -0.0000

Data Index: 790080 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 4.4607. Min Range: -4.4607

Max Act: 3.7775. Min Act: -0.0001

Data Index: 900326 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 4.4607. Min Range: -4.4607

Max Act: 3.3679. Min Act: -0.0001

Data Index: 1057135 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 4.4607. Min Range: -4.4607

Max Act: 3.4269. Min Act: -0.0001

Data Index: 982545 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 4.4607. Min Range: -4.4607

Max Act: 3.2476. Min Act: -0.0001

Data Index: 863218 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 4.4607. Min Range: -4.4607

Max Act: 3.1719. Min Act: -0.0000

Data Index: 778197 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 4.4607. Min Range: -4.4607

Max Act: 3.0371. Min Act: -0.0000

Data Index: 1130800 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 4.4607. Min Range: -4.4607

Max Act: 3.0242. Min Act: -0.0000

Data Index: 776427 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 4.4607. Min Range: -4.4607

Max Act: 2.9070. Min Act: -0.0000

Data Index: 1257407 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 4.4607. Min Range: -4.4607

Max Act: 2.8030. Min Act: -0.0000

Data Index: 620877 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 4.4607. Min Range: -4.4607

Max Act: 2.9080. Min Act: -0.0001

Data Index: 1115608 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 4.4607. Min Range: -4.4607

Max Act: 2.7653. Min Act: -0.0001

Data Index: 213986 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 4.4607. Min Range: -4.4607

Max Act: 3.1719. Min Act: -0.0000

Data Index: 258442 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 4.4607. Min Range: -4.4607

Max Act: 2.7014. Min Act: -0.0000

Data Index: 132616 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 4.4607. Min Range: -4.4607

Max Act: 2.5811. Min Act: -0.0000

Data Index: 1180301 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 4.4607. Min Range: -4.4607

Max Act: 2.8213. Min Act: -0.0000

Data Index: 1172758 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 4.4607. Min Range: -4.4607

Max Act: 2.6685. Min Act: -0.0000

Data Index: 751186 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 4.4607. Min Range: -4.4607

Max Act: 2.7997. Min Act: -0.0000

Data Index: 526878 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 4.4607. Min Range: -4.4607

Max Act: 2.6726. Min Act: -0.0001

Data Index: 310854 (C4 (Web Text))

Max Activating Token Index: 645