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

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

Neuron 257 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: 1.8884. Min Range: -1.8884

Max Act: 1.8884. Min Act: -0.0001

Data Index: 295534 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.8675. Min Act: -0.0001

Data Index: 470586 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.6685. Min Act: -0.0001

Data Index: 823520 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.3797. Min Act: -0.0001

Data Index: 1144432 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.4298. Min Act: -0.0001

Data Index: 1000750 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.5291. Min Act: -0.0001

Data Index: 505029 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.5032. Min Act: -0.0001

Data Index: 313584 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.2800. Min Act: -0.0001

Data Index: 1215240 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.4909. Min Act: -0.0000

Data Index: 158149 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.2448. Min Act: -0.0000

Data Index: 984990 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.4882. Min Act: -0.0001

Data Index: 242233 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.3991. Min Act: -0.0000

Data Index: 1085918 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.5074. Min Act: -0.0001

Data Index: 608963 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.3029. Min Act: -0.0001

Data Index: 599773 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.4848. Min Act: -0.0000

Data Index: 284755 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.4188. Min Act: -0.0001

Data Index: 1150894 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.4824. Min Act: -0.0001

Data Index: 324689 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.3433. Min Act: -0.0001

Data Index: 731096 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.4435. Min Act: -0.0001

Data Index: 385653 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.4161. Min Act: -0.0000

Data Index: 678161 (C4 (Web Text))

Max Activating Token Index: 212