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

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

Neuron 1798 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3717. Min Act: -0.0001

Data Index: 1167849 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3874. Min Act: -0.0001

Data Index: 706549 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3413. Min Act: -0.0001

Data Index: 239574 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3626. Min Act: -0.0001

Data Index: 176544 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3466. Min Act: -0.0001

Data Index: 1221377 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3515. Min Act: -0.0001

Data Index: 1117039 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3025. Min Act: -0.0001

Data Index: 156590 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3233. Min Act: -0.0001

Data Index: 743734 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3224. Min Act: -0.0001

Data Index: 1324919 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3191. Min Act: -0.0001

Data Index: 1169578 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1071811 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3031. Min Act: -0.0001

Data Index: 6741 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3168. Min Act: -0.0001

Data Index: 536599 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2942. Min Act: -0.0001

Data Index: 790365 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2845. Min Act: -0.0001

Data Index: 1282118 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2812. Min Act: -0.0001

Data Index: 596735 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2847. Min Act: -0.0001

Data Index: 1257852 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2724. Min Act: -0.0001

Data Index: 438578 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2715. Min Act: -0.0001

Data Index: 491086 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2850. Min Act: -0.0001

Data Index: 7058 (C4 (Web Text))

Max Activating Token Index: 311