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

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

Neuron 1116 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.3624. Min Act: -0.0001

Data Index: 657349 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.2248. Min Act: -0.0001

Data Index: 1281159 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.1049. Min Act: -0.0001

Data Index: 505141 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.1053. Min Act: -0.0001

Data Index: 565107 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0485. Min Act: -0.0001

Data Index: 816452 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0777. Min Act: -0.0001

Data Index: 709683 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0394. Min Act: -0.0001

Data Index: 1156356 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0390. Min Act: -0.0001

Data Index: 43688 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.1136. Min Act: -0.0001

Data Index: 986110 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0908. Min Act: -0.0001

Data Index: 131795 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0048. Min Act: -0.0001

Data Index: 668312 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9452. Min Act: -0.0001

Data Index: 730177 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9664. Min Act: -0.0001

Data Index: 447787 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9650. Min Act: -0.0001

Data Index: 220742 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9846. Min Act: -0.0001

Data Index: 205709 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0110. Min Act: -0.0001

Data Index: 77715 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9503. Min Act: -0.0001

Data Index: 180195 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.8865. Min Act: -0.0001

Data Index: 1017821 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9406. Min Act: -0.0001

Data Index: 410876 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0214. Min Act: -0.0001

Data Index: 1143483 (C4 (Web Text))

Max Activating Token Index: 206