Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1865 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.3128. Min Act: -0.0001

Data Index: 935439 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0717. Min Act: -0.0001

Data Index: 830274 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0194. Min Act: -0.0001

Data Index: 1117689 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0255. Min Act: -0.0001

Data Index: 701718 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9430. Min Act: -0.0001

Data Index: 331648 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0394. Min Act: -0.0001

Data Index: 1012948 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9831. Min Act: -0.0001

Data Index: 1280421 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9433. Min Act: -0.0001

Data Index: 80446 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9608. Min Act: -0.0001

Data Index: 181956 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9379. Min Act: -0.0001

Data Index: 1092754 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9934. Min Act: -0.0001

Data Index: 835261 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9700. Min Act: -0.0001

Data Index: 126119 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8945. Min Act: -0.0001

Data Index: 1024777 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8539. Min Act: -0.0001

Data Index: 971746 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8719. Min Act: -0.0001

Data Index: 626311 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8929. Min Act: -0.0001

Data Index: 1208330 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8162. Min Act: -0.0001

Data Index: 853985 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8633. Min Act: -0.0001

Data Index: 1325267 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.7952. Min Act: -0.0001

Data Index: 1185270 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9007. Min Act: -0.0001

Data Index: 71616 (C4 (Web Text))

Max Activating Token Index: 697