Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 522 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.1093. Min Range: -4.1093

Max Act: 4.1093. Min Act: -0.0001

Data Index: 92290 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.7395. Min Act: -0.0001

Data Index: 473490 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.2575. Min Act: -0.0001

Data Index: 686862 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.0139. Min Act: -0.0001

Data Index: 889030 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.9818. Min Act: -0.0000

Data Index: 1221682 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.0040. Min Act: -0.0001

Data Index: 3958 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.8159. Min Act: -0.0001

Data Index: 88325 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.9714. Min Act: -0.0001

Data Index: 1232627 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.8875. Min Act: -0.0001

Data Index: 1223325 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.7647. Min Act: -0.0001

Data Index: 355667 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.8856. Min Act: -0.0001

Data Index: 306584 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.7324. Min Act: -0.0001

Data Index: 115402 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.8437. Min Act: -0.0000

Data Index: 1153175 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.5832. Min Act: -0.0001

Data Index: 175462 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.6516. Min Act: -0.0001

Data Index: 417647 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.7681. Min Act: -0.0001

Data Index: 245579 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.7553. Min Act: -0.0001

Data Index: 528821 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.7199. Min Act: -0.0001

Data Index: 354950 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.6610. Min Act: -0.0001

Data Index: 1248647 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 4.1093. Min Range: -4.1093

Max Act: 2.7883. Min Act: -0.0001

Data Index: 1027093 (C4 (Web Text))

Max Activating Token Index: 461