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

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

Neuron 1926 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.6200. Min Act: -0.0003

Data Index: 901466 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.5338. Min Act: -0.0003

Data Index: 348798 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4237. Min Act: -0.0003

Data Index: 339977 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4760. Min Act: -0.0003

Data Index: 427392 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4591. Min Act: -0.0003

Data Index: 1240615 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4703. Min Act: -0.0003

Data Index: 647169 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4200. Min Act: -0.0003

Data Index: 1290909 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4434. Min Act: -0.0003

Data Index: 1061334 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4565. Min Act: -0.0003

Data Index: 1501223 (Python Code)

Max Activating Token Index: 921

Text #9

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4079. Min Act: -0.0003

Data Index: 1409449 (Python Code)

Max Activating Token Index: 975

Text #10

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3853. Min Act: -0.0003

Data Index: 96921 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3407. Min Act: -0.0003

Data Index: 1014764 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4073. Min Act: -0.0003

Data Index: 524174 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3903. Min Act: -0.0003

Data Index: 64021 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4402. Min Act: -0.0003

Data Index: 421739 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3571. Min Act: -0.0003

Data Index: 1222886 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3924. Min Act: -0.0003

Data Index: 1340407 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3925. Min Act: -0.0003

Data Index: 85405 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.2848. Min Act: -0.0003

Data Index: 947434 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.2587. Min Act: -0.0003

Data Index: 487422 (C4 (Web Text))

Max Activating Token Index: 669