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

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

Neuron 3158 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.9008. Min Act: -0.0000

Data Index: 962994 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.8536. Min Act: -0.0000

Data Index: 311057 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.8297. Min Act: -0.0000

Data Index: 5303 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1053979 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7978. Min Act: -0.0000

Data Index: 237071 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1053956 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7494. Min Act: -0.0000

Data Index: 454770 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7630. Min Act: -0.0000

Data Index: 578573 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7604. Min Act: -0.0000

Data Index: 227611 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7387. Min Act: -0.0000

Data Index: 869720 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7136. Min Act: -0.0000

Data Index: 690961 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7605. Min Act: -0.0000

Data Index: 68392 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7651. Min Act: -0.0000

Data Index: 77696 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7224. Min Act: -0.0000

Data Index: 270265 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7049. Min Act: -0.0000

Data Index: 632140 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1165427 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7287. Min Act: -0.0000

Data Index: 640784 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6414. Min Act: -0.0000

Data Index: 499029 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6525. Min Act: -0.0000

Data Index: 553523 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1313952 (C4 (Web Text))

Max Activating Token Index: 519