Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1427 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5247. Min Act: -0.0001

Data Index: 46814 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5686. Min Act: -0.0001

Data Index: 560066 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5180. Min Act: -0.0001

Data Index: 523325 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4957. Min Act: -0.0001

Data Index: 1190569 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4563. Min Act: -0.0001

Data Index: 941159 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4477. Min Act: -0.0001

Data Index: 949024 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4406. Min Act: -0.0001

Data Index: 423539 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4247. Min Act: -0.0001

Data Index: 316903 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4084. Min Act: -0.0001

Data Index: 1329530 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4455. Min Act: -0.0001

Data Index: 260610 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4221. Min Act: -0.0001

Data Index: 680826 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4198. Min Act: -0.0001

Data Index: 55882 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.3994. Min Act: -0.0001

Data Index: 19940 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4269. Min Act: -0.0001

Data Index: 430126 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4073. Min Act: -0.0001

Data Index: 230289 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.3785. Min Act: -0.0001

Data Index: 279116 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4035. Min Act: -0.0001

Data Index: 1198554 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4170. Min Act: -0.0001

Data Index: 253702 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4012. Min Act: -0.0001

Data Index: 320157 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4282. Min Act: -0.0001

Data Index: 485105 (C4 (Web Text))

Max Activating Token Index: 516