Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4841 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.2894. Min Act: -0.0001

Data Index: 849525 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.1017. Min Act: -0.0001

Data Index: 744158 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.1731. Min Act: -0.0001

Data Index: 639960 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.0838. Min Act: -0.0001

Data Index: 797948 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.1272. Min Act: -0.0001

Data Index: 1104576 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.0463. Min Act: -0.0001

Data Index: 1059738 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 1.2894. Min Range: -1.2894

Max Act: 0.9486. Min Act: -0.0001

Data Index: 610101 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 1.2894. Min Range: -1.2894

Max Act: 0.9413. Min Act: -0.0001

Data Index: 1222858 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 1.2894. Min Range: -1.2894

Max Act: 0.9347. Min Act: -0.0001

Data Index: 426523 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 1.2894. Min Range: -1.2894

Max Act: 0.8837. Min Act: -0.0001

Data Index: 1326141 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.0216. Min Act: -0.0001

Data Index: 112696 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 1.2894. Min Range: -1.2894

Max Act: 0.8423. Min Act: -0.0001

Data Index: 971640 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 1.2894. Min Range: -1.2894

Max Act: 0.8308. Min Act: -0.0001

Data Index: 738638 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 1.2894. Min Range: -1.2894

Max Act: 0.9091. Min Act: -0.0001

Data Index: 456917 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 1.2894. Min Range: -1.2894

Max Act: 0.8952. Min Act: -0.0001

Data Index: 852825 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 1.2894. Min Range: -1.2894

Max Act: 0.9320. Min Act: -0.0001

Data Index: 691504 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 1.2894. Min Range: -1.2894

Max Act: 0.8462. Min Act: -0.0001

Data Index: 1050281 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 1.2894. Min Range: -1.2894

Max Act: 0.8343. Min Act: -0.0001

Data Index: 2145 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 1.2894. Min Range: -1.2894

Max Act: 0.8471. Min Act: -0.0001

Data Index: 1310785 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 1.2894. Min Range: -1.2894

Max Act: 0.7920. Min Act: -0.0001

Data Index: 409113 (C4 (Web Text))

Max Activating Token Index: 61