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

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

Neuron 3839 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.7693. Min Act: -0.0001

Data Index: 814949 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.6509. Min Act: -0.0001

Data Index: 1331667 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.6480. Min Act: -0.0001

Data Index: 904703 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.6538. Min Act: -0.0001

Data Index: 628924 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.6179. Min Act: -0.0001

Data Index: 1125153 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.6122. Min Act: -0.0001

Data Index: 437832 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5835. Min Act: -0.0001

Data Index: 689062 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5916. Min Act: -0.0001

Data Index: 1298600 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.6086. Min Act: -0.0001

Data Index: 1132734 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5443. Min Act: -0.0001

Data Index: 541534 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.6028. Min Act: -0.0001

Data Index: 1336772 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5631. Min Act: -0.0001

Data Index: 1093509 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5809. Min Act: -0.0001

Data Index: 377824 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.6225. Min Act: -0.0001

Data Index: 758069 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5404. Min Act: -0.0001

Data Index: 740321 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5722. Min Act: -0.0001

Data Index: 947736 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.6137. Min Act: -0.0001

Data Index: 88110 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5904. Min Act: -0.0001

Data Index: 787109 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5863. Min Act: -0.0001

Data Index: 276455 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.7693. Min Range: -0.7693

Max Act: 0.5872. Min Act: -0.0001

Data Index: 1256793 (C4 (Web Text))

Max Activating Token Index: 453