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

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

Neuron 897 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: 1.5061. Min Range: -1.5061

Max Act: 1.4872. Min Act: -0.0002

Data Index: 714829 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.5061. Min Act: -0.0002

Data Index: 728784 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4791. Min Act: -0.0003

Data Index: 1099399 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4050. Min Act: -0.0002

Data Index: 792616 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3882. Min Act: -0.0002

Data Index: 354381 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3900. Min Act: -0.0002

Data Index: 961905 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3897. Min Act: -0.0002

Data Index: 660516 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3414. Min Act: -0.0002

Data Index: 841611 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3734. Min Act: -0.0002

Data Index: 651841 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3705. Min Act: -0.0002

Data Index: 1155580 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3407. Min Act: -0.0002

Data Index: 110092 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3489. Min Act: -0.0002

Data Index: 515154 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3305. Min Act: -0.0002

Data Index: 1348316 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3228. Min Act: -0.0003

Data Index: 780472 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3169. Min Act: -0.0002

Data Index: 559695 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3198. Min Act: -0.0002

Data Index: 38460 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2749. Min Act: -0.0002

Data Index: 1035033 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2827. Min Act: -0.0002

Data Index: 1259327 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2726. Min Act: -0.0002

Data Index: 895726 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2808. Min Act: -0.0002

Data Index: 142432 (C4 (Web Text))

Max Activating Token Index: 839