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

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

Neuron 5336 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3396. Min Act: -0.0001

Data Index: 1625812 (Python Code)

Max Activating Token Index: 596

Text #1

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3412. Min Act: -0.0001

Data Index: 180773 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3174. Min Act: -0.0001

Data Index: 622777 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3152. Min Act: -0.0001

Data Index: 1542465 (Python Code)

Max Activating Token Index: 720

Text #4

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3059. Min Act: -0.0001

Data Index: 1654637 (Python Code)

Max Activating Token Index: 561

Text #5

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2990. Min Act: -0.0001

Data Index: 1539887 (Python Code)

Max Activating Token Index: 803

Text #6

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3054. Min Act: -0.0001

Data Index: 1611499 (Python Code)

Max Activating Token Index: 779

Text #7

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2988. Min Act: -0.0001

Data Index: 1103247 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3056. Min Act: -0.0001

Data Index: 175516 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2944. Min Act: -0.0001

Data Index: 1584908 (Python Code)

Max Activating Token Index: 833

Text #10

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2948. Min Act: -0.0001

Data Index: 1637231 (Python Code)

Max Activating Token Index: 699

Text #11

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2994. Min Act: -0.0001

Data Index: 96616 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2853. Min Act: -0.0001

Data Index: 1654234 (Python Code)

Max Activating Token Index: 845

Text #13

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2839. Min Act: -0.0001

Data Index: 1487593 (Python Code)

Max Activating Token Index: 169

Text #14

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2878. Min Act: -0.0001

Data Index: 1418534 (Python Code)

Max Activating Token Index: 330

Text #15

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2870. Min Act: -0.0001

Data Index: 827207 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2888. Min Act: -0.0001

Data Index: 1374622 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2842. Min Act: -0.0001

Data Index: 1620863 (Python Code)

Max Activating Token Index: 307

Text #18

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2808. Min Act: -0.0001

Data Index: 1408907 (Python Code)

Max Activating Token Index: 46

Text #19

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2887. Min Act: -0.0001

Data Index: 1389548 (Python Code)

Max Activating Token Index: 181