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

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

Neuron 2607 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.8825. Min Act: -0.0001

Data Index: 1139942 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.8269. Min Act: -0.0001

Data Index: 80615 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7882. Min Act: -0.0001

Data Index: 79596 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7525. Min Act: -0.0001

Data Index: 697684 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6910. Min Act: -0.0001

Data Index: 1048640 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6147. Min Act: -0.0001

Data Index: 580962 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7141. Min Act: -0.0001

Data Index: 993589 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6912. Min Act: -0.0001

Data Index: 897898 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6621. Min Act: -0.0001

Data Index: 779509 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6458. Min Act: -0.0001

Data Index: 952667 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6235. Min Act: -0.0001

Data Index: 792235 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.5675. Min Act: -0.0001

Data Index: 1291918 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.5651. Min Act: -0.0001

Data Index: 489555 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.5703. Min Act: -0.0001

Data Index: 753152 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.5864. Min Act: -0.0001

Data Index: 545724 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.4925. Min Act: -0.0001

Data Index: 407925 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.5561. Min Act: -0.0001

Data Index: 453294 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.5601. Min Act: -0.0001

Data Index: 728758 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.5311. Min Act: -0.0001

Data Index: 439245 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.5349. Min Act: -0.0001

Data Index: 1202787 (C4 (Web Text))

Max Activating Token Index: 216