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

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

Neuron 2013 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.9453. Min Act: -0.0001

Data Index: 698155 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.8514. Min Act: -0.0000

Data Index: 454605 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.8578. Min Act: -0.0001

Data Index: 522375 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.8030. Min Act: -0.0001

Data Index: 300320 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.7671. Min Act: -0.0001

Data Index: 1287827 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.7696. Min Act: -0.0001

Data Index: 1068403 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.7137. Min Act: -0.0001

Data Index: 785487 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.7006. Min Act: -0.0001

Data Index: 542506 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6911. Min Act: -0.0001

Data Index: 1262009 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6990. Min Act: -0.0000

Data Index: 600429 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6929. Min Act: -0.0001

Data Index: 76737 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6512. Min Act: -0.0001

Data Index: 28101 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6711. Min Act: -0.0001

Data Index: 974345 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6425. Min Act: -0.0001

Data Index: 582139 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6435. Min Act: -0.0001

Data Index: 602952 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6376. Min Act: -0.0001

Data Index: 343241 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6581. Min Act: -0.0000

Data Index: 192219 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6582. Min Act: -0.0001

Data Index: 13717 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6522. Min Act: -0.0001

Data Index: 567192 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6666. Min Act: -0.0001

Data Index: 740888 (C4 (Web Text))

Max Activating Token Index: 861