Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2706 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.7169. Min Act: -0.0000

Data Index: 429113 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6517. Min Act: -0.0000

Data Index: 58146 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.6321. Min Act: -0.0000

Data Index: 998775 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.5991. Min Act: -0.0000

Data Index: 261941 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.5514. Min Act: -0.0000

Data Index: 705168 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1054086 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1258677 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.5300. Min Act: -0.0000

Data Index: 903200 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.5249. Min Act: -0.0000

Data Index: 814391 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.5298. Min Act: -0.0000

Data Index: 688220 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.5139. Min Act: -0.0000

Data Index: 466498 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.5236. Min Act: -0.0000

Data Index: 751620 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.4885. Min Act: -0.0000

Data Index: 409960 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.4914. Min Act: -0.0000

Data Index: 117718 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1024133 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.4503. Min Act: -0.0000

Data Index: 360662 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.4762. Min Act: 0.0000

Data Index: 960548 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.4581. Min Act: 0.0000

Data Index: 605402 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1347013 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 0.7169. Min Range: -0.7169

Max Act: 0.4545. Min Act: -0.0000

Data Index: 166810 (C4 (Web Text))

Max Activating Token Index: 791