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

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

Neuron 3858 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.9542. Min Act: -0.0000

Data Index: 853050 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.6717. Min Act: -0.0000

Data Index: 196453 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.7618. Min Act: -0.0000

Data Index: 260261 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.9161. Min Act: -0.0000

Data Index: 1289530 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.7008. Min Act: -0.0000

Data Index: 1082910 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.6781. Min Act: -0.0000

Data Index: 2896 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.6805. Min Act: -0.0000

Data Index: 1003047 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.6337. Min Act: -0.0000

Data Index: 253718 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.5458. Min Act: -0.0000

Data Index: 1153167 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.4947. Min Act: -0.0000

Data Index: 547836 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.5722. Min Act: -0.0000

Data Index: 182190 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.5327. Min Act: -0.0000

Data Index: 495820 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.5302. Min Act: -0.0000

Data Index: 1289483 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.5677. Min Act: -0.0000

Data Index: 1026793 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.4499. Min Act: -0.0000

Data Index: 993262 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.3841. Min Act: -0.0000

Data Index: 81654 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.4458. Min Act: -0.0000

Data Index: 146049 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.2739. Min Act: -0.0000

Data Index: 1343713 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.3989. Min Act: -0.0000

Data Index: 1048516 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 1.9542. Min Range: -1.9542

Max Act: 1.4669. Min Act: -0.0000

Data Index: 1341712 (C4 (Web Text))

Max Activating Token Index: 506