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

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

Neuron 4534 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9197. Min Range: -2.9197

Max Act: 2.9197. Min Act: -0.0000

Data Index: 931610 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 2.9197. Min Range: -2.9197

Max Act: 2.1184. Min Act: -0.0000

Data Index: 1302127 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 2.9197. Min Range: -2.9197

Max Act: 2.2288. Min Act: -0.0000

Data Index: 962499 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.8414. Min Act: -0.0000

Data Index: 980928 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.9175. Min Act: -0.0000

Data Index: 905941 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.8452. Min Act: -0.0001

Data Index: 380094 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 2.9197. Min Range: -2.9197

Max Act: 2.0502. Min Act: -0.0000

Data Index: 1056033 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.8599. Min Act: -0.0000

Data Index: 717913 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.7411. Min Act: -0.0001

Data Index: 989143 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.8331. Min Act: -0.0000

Data Index: 441985 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.7198. Min Act: -0.0000

Data Index: 1097440 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.7999. Min Act: -0.0000

Data Index: 478498 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.7892. Min Act: -0.0000

Data Index: 408925 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.7714. Min Act: -0.0000

Data Index: 1084237 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.9668. Min Act: -0.0000

Data Index: 713585 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.6460. Min Act: -0.0000

Data Index: 756592 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.6346. Min Act: -0.0000

Data Index: 504727 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.7119. Min Act: -0.0000

Data Index: 662496 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.5718. Min Act: -0.0000

Data Index: 1169655 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 2.9197. Min Range: -2.9197

Max Act: 1.4916. Min Act: -0.0001

Data Index: 1038530 (C4 (Web Text))

Max Activating Token Index: 922