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

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

Neuron 1570 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.9489. Min Act: -0.0000

Data Index: 1206823 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1022819 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6069. Min Act: -0.0000

Data Index: 135794 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6244. Min Act: -0.0000

Data Index: 408802 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.5703. Min Act: -0.0000

Data Index: 950489 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1131356 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.5612. Min Act: -0.0000

Data Index: 918538 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1102975 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.5420. Min Act: 0.0001

Data Index: 339904 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.5160. Min Act: -0.0000

Data Index: 614187 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.5273. Min Act: -0.0000

Data Index: 450063 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.4910. Min Act: -0.0000

Data Index: 8103 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.4893. Min Act: -0.0000

Data Index: 393605 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.4878. Min Act: 0.0001

Data Index: 333443 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.4830. Min Act: 0.0000

Data Index: 57569 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.4957. Min Act: 0.0001

Data Index: 929941 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.4644. Min Act: -0.0000

Data Index: 398214 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.4799. Min Act: -0.0000

Data Index: 520084 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1116792 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.4546. Min Act: -0.0000

Data Index: 782713 (C4 (Web Text))

Max Activating Token Index: 224