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

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

Neuron 2174 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.1624. Min Act: -0.0000

Data Index: 1047860 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.1328. Min Act: -0.0000

Data Index: 390774 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0838. Min Act: -0.0000

Data Index: 731532 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0466. Min Act: -0.0000

Data Index: 397897 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0846. Min Act: -0.0000

Data Index: 610279 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1226450 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1095882 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0210. Min Act: 0.0000

Data Index: 459304 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9863. Min Act: -0.0000

Data Index: 952483 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1031842 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9277. Min Act: -0.0000

Data Index: 649144 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9490. Min Act: -0.0000

Data Index: 331220 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9666. Min Act: -0.0000

Data Index: 800619 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9375. Min Act: -0.0000

Data Index: 677085 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9581. Min Act: -0.0000

Data Index: 316375 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9200. Min Act: -0.0000

Data Index: 593487 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9163. Min Act: -0.0000

Data Index: 206789 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8862. Min Act: -0.0000

Data Index: 160425 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8830. Min Act: -0.0000

Data Index: 308423 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8787. Min Act: -0.0000

Data Index: 169639 (C4 (Web Text))

Max Activating Token Index: 26