Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4908 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5764. Min Act: -0.0000

Data Index: 786082 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5566. Min Act: -0.0000

Data Index: 846196 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1009735 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5336. Min Act: 0.0000

Data Index: 605059 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1251920 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5162. Min Act: -0.0000

Data Index: 781687 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1315823 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4666. Min Act: -0.0000

Data Index: 23179 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4427. Min Act: 0.0000

Data Index: 1497501 (Python Code)

Max Activating Token Index: 999

Text #9

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.3990. Min Act: -0.0000

Data Index: 24704 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4079. Min Act: -0.0000

Data Index: 102170 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1242576 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1280289 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1130548 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4034. Min Act: -0.0000

Data Index: 9568 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.3997. Min Act: 0.0000

Data Index: 625040 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1389561 (Python Code)

Max Activating Token Index: 965

Text #17

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1460426 (Python Code)

Max Activating Token Index: 1000

Text #18

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.3905. Min Act: -0.0000

Data Index: 20626 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4277. Min Act: -0.0000

Data Index: 680442 (C4 (Web Text))

Max Activating Token Index: 230