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

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

Neuron 22 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5594. Min Act: -0.0000

Data Index: 195605 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5044. Min Act: -0.0000

Data Index: 489400 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5457. Min Act: -0.0000

Data Index: 988773 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1342217 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1126393 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4499. Min Act: -0.0001

Data Index: 65511 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4589. Min Act: -0.0001

Data Index: 117696 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4363. Min Act: -0.0000

Data Index: 112264 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1295481 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4406. Min Act: -0.0000

Data Index: 972535 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4659. Min Act: -0.0000

Data Index: 862039 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4276. Min Act: -0.0000

Data Index: 214957 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4176. Min Act: -0.0000

Data Index: 649911 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4008. Min Act: -0.0001

Data Index: 1065451 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.3843. Min Act: -0.0000

Data Index: 222622 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.3787. Min Act: -0.0001

Data Index: 898526 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4080. Min Act: -0.0000

Data Index: 562910 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1135221 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.3998. Min Act: -0.0000

Data Index: 86216 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.3872. Min Act: -0.0001

Data Index: 768198 (C4 (Web Text))

Max Activating Token Index: 172