Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 490 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.7536. Min Act: -0.0001

Data Index: 711913 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.7580. Min Act: -0.0001

Data Index: 373095 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.6863. Min Act: -0.0001

Data Index: 803659 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.6311. Min Act: -0.0001

Data Index: 647552 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.6552. Min Act: -0.0001

Data Index: 893589 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.6589. Min Act: -0.0001

Data Index: 988681 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.5361. Min Act: -0.0001

Data Index: 1205875 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.5864. Min Act: -0.0001

Data Index: 647885 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4574. Min Act: -0.0001

Data Index: 613249 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4447. Min Act: -0.0001

Data Index: 483495 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.5905. Min Act: -0.0001

Data Index: 514954 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4570. Min Act: -0.0001

Data Index: 1176485 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3265. Min Act: -0.0001

Data Index: 754877 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4964. Min Act: -0.0001

Data Index: 522735 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4140. Min Act: -0.0001

Data Index: 1124435 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.2976. Min Act: -0.0001

Data Index: 503194 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4541. Min Act: -0.0001

Data Index: 409586 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4156. Min Act: -0.0001

Data Index: 1028766 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4519. Min Act: -0.0001

Data Index: 474477 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4245. Min Act: -0.0001

Data Index: 829646 (C4 (Web Text))

Max Activating Token Index: 75