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

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

Neuron 195 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1388. Min Act: -0.0000

Data Index: 236031 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1310. Min Act: -0.0000

Data Index: 170250 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1280. Min Act: -0.0000

Data Index: 144324 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1169221 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1326. Min Act: -0.0000

Data Index: 732241 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1199805 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1127. Min Act: -0.0000

Data Index: 814598 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1061. Min Act: -0.0000

Data Index: 84250 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1058. Min Act: -0.0000

Data Index: 154043 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1082063 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0990. Min Act: -0.0000

Data Index: 551948 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1018. Min Act: -0.0000

Data Index: 342292 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0998. Min Act: -0.0000

Data Index: 660490 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1142946 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0990. Min Act: -0.0000

Data Index: 172330 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0963. Min Act: -0.0000

Data Index: 459529 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0923. Min Act: -0.0000

Data Index: 308934 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0894. Min Act: -0.0000

Data Index: 444064 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0953. Min Act: -0.0000

Data Index: 788025 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0890. Min Act: -0.0000

Data Index: 444183 (C4 (Web Text))

Max Activating Token Index: 748