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

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

Neuron 3706 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: 0.7622. Min Range: -0.7622

Max Act: 0.7622. Min Act: -0.0001

Data Index: 668884 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.7252. Min Act: -0.0001

Data Index: 619533 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.7523. Min Act: -0.0001

Data Index: 630954 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.7129. Min Act: -0.0001

Data Index: 1191778 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.6642. Min Act: -0.0001

Data Index: 989798 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.6704. Min Act: -0.0001

Data Index: 800001 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.6727. Min Act: -0.0001

Data Index: 580734 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.6470. Min Act: -0.0001

Data Index: 1078916 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.6465. Min Act: -0.0001

Data Index: 1022106 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5908. Min Act: -0.0001

Data Index: 1153542 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5926. Min Act: -0.0001

Data Index: 131304 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5864. Min Act: -0.0001

Data Index: 683431 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5841. Min Act: -0.0001

Data Index: 761026 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.6051. Min Act: -0.0001

Data Index: 1181263 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5824. Min Act: -0.0001

Data Index: 61468 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5517. Min Act: -0.0001

Data Index: 519837 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5884. Min Act: -0.0001

Data Index: 45079 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5819. Min Act: -0.0001

Data Index: 670093 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5626. Min Act: -0.0001

Data Index: 98078 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5977. Min Act: -0.0001

Data Index: 846429 (C4 (Web Text))

Max Activating Token Index: 237