Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3215 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.8815. Min Act: -0.0001

Data Index: 541658 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.7893. Min Act: -0.0001

Data Index: 772213 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.3411. Min Act: -0.0001

Data Index: 941396 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.4038. Min Act: -0.0001

Data Index: 16703 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.7945. Min Act: -0.0001

Data Index: 447150 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.4245. Min Act: -0.0001

Data Index: 604117 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.2057. Min Act: -0.0001

Data Index: 150178 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.4811. Min Act: -0.0001

Data Index: 1081832 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.5898. Min Act: -0.0001

Data Index: 576186 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.4178. Min Act: -0.0001

Data Index: 999437 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 5.8815. Min Range: -5.8815

Max Act: 4.9261. Min Act: -0.0001

Data Index: 514312 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 5.8815. Min Range: -5.8815

Max Act: 4.7316. Min Act: -0.0001

Data Index: 1315968 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.0081. Min Act: -0.0001

Data Index: 1073067 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.4326. Min Act: -0.0001

Data Index: 316399 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.2882. Min Act: -0.0001

Data Index: 1046127 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.2548. Min Act: -0.0001

Data Index: 553889 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.2704. Min Act: -0.0001

Data Index: 1039666 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 5.8815. Min Range: -5.8815

Max Act: 5.2237. Min Act: -0.0001

Data Index: 681055 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 5.8815. Min Range: -5.8815

Max Act: 4.3651. Min Act: -0.0001

Data Index: 1003093 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 5.8815. Min Range: -5.8815

Max Act: 4.9112. Min Act: -0.0001

Data Index: 1265440 (C4 (Web Text))

Max Activating Token Index: 815