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

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

Neuron 2739 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: 1.4740. Min Range: -1.4740

Max Act: 1.4740. Min Act: -0.0000

Data Index: 1015479 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 1.4740. Min Range: -1.4740

Max Act: 1.1708. Min Act: -0.0000

Data Index: 446012 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.4740. Min Range: -1.4740

Max Act: 1.0936. Min Act: -0.0001

Data Index: 326757 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.4740. Min Range: -1.4740

Max Act: 1.1275. Min Act: -0.0001

Data Index: 987157 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.9591. Min Act: -0.0001

Data Index: 488001 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.8499. Min Act: -0.0001

Data Index: 956881 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.7244. Min Act: -0.0001

Data Index: 102031 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.7255. Min Act: -0.0001

Data Index: 197556 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.6928. Min Act: -0.0001

Data Index: 713467 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.6797. Min Act: -0.0001

Data Index: 585591 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.6987. Min Act: -0.0000

Data Index: 673759 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.6714. Min Act: -0.0001

Data Index: 236203 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.6955. Min Act: -0.0000

Data Index: 827854 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.6706. Min Act: -0.0001

Data Index: 130509 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.7127. Min Act: -0.0001

Data Index: 396602 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1232775 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.7094. Min Act: -0.0001

Data Index: 591194 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.6874. Min Act: -0.0001

Data Index: 806163 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.6817. Min Act: -0.0001

Data Index: 632355 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 1.4740. Min Range: -1.4740

Max Act: 0.6636. Min Act: -0.0001

Data Index: 191129 (C4 (Web Text))

Max Activating Token Index: 372