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

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

Neuron 2791 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.2089. Min Act: -0.0000

Data Index: 201284 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1899. Min Act: -0.0000

Data Index: 768049 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1120658 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1879. Min Act: -0.0000

Data Index: 659181 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1036677 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1862. Min Act: -0.0000

Data Index: 300526 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1836. Min Act: -0.0001

Data Index: 502703 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1732. Min Act: -0.0001

Data Index: 826894 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1823. Min Act: -0.0000

Data Index: 944023 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1668. Min Act: -0.0000

Data Index: 922937 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1611. Min Act: -0.0001

Data Index: 427428 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1591. Min Act: -0.0000

Data Index: 1136113 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1621. Min Act: -0.0001

Data Index: 490264 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1600. Min Act: -0.0000

Data Index: 96174 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1499. Min Act: -0.0000

Data Index: 140850 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1488. Min Act: -0.0000

Data Index: 938601 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1428. Min Act: -0.0000

Data Index: 907579 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1371. Min Act: -0.0001

Data Index: 575251 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1462. Min Act: -0.0000

Data Index: 251292 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1469. Min Act: -0.0000

Data Index: 413027 (C4 (Web Text))

Max Activating Token Index: 147