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

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

Neuron 2842 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: 0.6645. Min Range: -0.6645

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1082751 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6585. Min Act: -0.0001

Data Index: 303534 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1204648 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6090. Min Act: -0.0000

Data Index: 119025 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1179125 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1117742 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1051474 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5621. Min Act: -0.0000

Data Index: 571905 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1000232 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5324. Min Act: -0.0000

Data Index: 904305 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5643. Min Act: -0.0000

Data Index: 712565 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5407. Min Act: -0.0000

Data Index: 241293 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5246. Min Act: 0.0000

Data Index: 255072 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1140305 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5193. Min Act: -0.0000

Data Index: 956081 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5097. Min Act: -0.0000

Data Index: 7004 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5112. Min Act: -0.0000

Data Index: 302345 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5041. Min Act: -0.0000

Data Index: 153835 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4961. Min Act: -0.0000

Data Index: 795177 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4896. Min Act: -0.0000

Data Index: 339947 (C4 (Web Text))

Max Activating Token Index: 944