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

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

Neuron 2781 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.5242. Min Act: -0.0000

Data Index: 767965 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1259995 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3536. Min Act: -0.0000

Data Index: 967981 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3406. Min Act: -0.0000

Data Index: 995918 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3444. Min Act: -0.0000

Data Index: 689954 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1017130 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3319. Min Act: -0.0000

Data Index: 960795 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3434. Min Act: -0.0000

Data Index: 368447 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3168. Min Act: -0.0000

Data Index: 662785 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.2978. Min Act: -0.0000

Data Index: 513838 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3149. Min Act: -0.0000

Data Index: 156156 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3123. Min Act: -0.0000

Data Index: 91365 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3083. Min Act: -0.0000

Data Index: 907561 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3071. Min Act: -0.0000

Data Index: 961680 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3169. Min Act: -0.0000

Data Index: 929661 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3032. Min Act: -0.0000

Data Index: 256055 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.2877. Min Act: -0.0000

Data Index: 780732 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.2894. Min Act: -0.0000

Data Index: 428465 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.2996. Min Act: -0.0000

Data Index: 378469 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.2761. Min Act: -0.0000

Data Index: 782851 (C4 (Web Text))

Max Activating Token Index: 570