Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5028 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.5556. Min Act: -0.0001

Data Index: 477789 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4148. Min Act: -0.0000

Data Index: 340412 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1349013 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3703. Min Act: -0.0000

Data Index: 19812 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1330291 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3731. Min Act: -0.0001

Data Index: 1061198 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3840. Min Act: -0.0001

Data Index: 98954 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3843. Min Act: -0.0001

Data Index: 782680 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3295. Min Act: -0.0000

Data Index: 937743 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3388. Min Act: -0.0000

Data Index: 897466 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3215. Min Act: -0.0001

Data Index: 40355 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3525. Min Act: -0.0001

Data Index: 13229 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3217. Min Act: -0.0000

Data Index: 910697 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3012. Min Act: -0.0000

Data Index: 28360 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3171. Min Act: -0.0001

Data Index: 808504 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.2539. Min Act: -0.0000

Data Index: 932561 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3083. Min Act: -0.0000

Data Index: 61784 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.2746. Min Act: -0.0000

Data Index: 609957 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.2601. Min Act: -0.0001

Data Index: 131819 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.2659. Min Act: -0.0000

Data Index: 124510 (C4 (Web Text))

Max Activating Token Index: 31