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

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

Neuron 5601 in Layer 1

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: 0.1040. Min Range: -0.1040

Max Act: 0.1040. Min Act: -0.0002

Data Index: 386693 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1017. Min Act: -0.0002

Data Index: 757826 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1195077 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1212262 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0945. Min Act: -0.0002

Data Index: 135666 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0934. Min Act: -0.0002

Data Index: 505836 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0941. Min Act: -0.0002

Data Index: 879100 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0919. Min Act: -0.0002

Data Index: 295953 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0914. Min Act: -0.0002

Data Index: 171774 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0912. Min Act: -0.0002

Data Index: 450235 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0916. Min Act: -0.0002

Data Index: 363853 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0914. Min Act: -0.0002

Data Index: 557326 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0889. Min Act: -0.0002

Data Index: 780117 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0916. Min Act: -0.0002

Data Index: 615976 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1020754 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1038649 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0895. Min Act: -0.0002

Data Index: 622952 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0911. Min Act: -0.0002

Data Index: 276374 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1053844 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0879. Min Act: -0.0002

Data Index: 715044 (C4 (Web Text))

Max Activating Token Index: 286