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

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

Neuron 4594 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: 0.5778. Min Range: -0.5778

Max Act: 0.5468. Min Act: -0.0001

Data Index: 1131710 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.5778. Min Act: -0.0001

Data Index: 500866 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.5005. Min Act: -0.0001

Data Index: 1150152 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.5019. Min Act: -0.0001

Data Index: 1140009 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.4228. Min Act: -0.0001

Data Index: 60093 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.4932. Min Act: -0.0001

Data Index: 500079 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.5050. Min Act: -0.0001

Data Index: 271677 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.4988. Min Act: -0.0001

Data Index: 52697 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.5174. Min Act: -0.0001

Data Index: 359468 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.5296. Min Act: -0.0001

Data Index: 181940 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1027733 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.4749. Min Act: -0.0001

Data Index: 120938 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.5161. Min Act: -0.0001

Data Index: 811118 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.4633. Min Act: -0.0001

Data Index: 564577 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.5096. Min Act: -0.0001

Data Index: 955078 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.5584. Min Act: -0.0001

Data Index: 297815 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.4819. Min Act: -0.0001

Data Index: 955382 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.4481. Min Act: -0.0001

Data Index: 155666 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.4606. Min Act: -0.0001

Data Index: 759102 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.5778. Min Range: -0.5778

Max Act: 0.4011. Min Act: -0.0001

Data Index: 575808 (C4 (Web Text))

Max Activating Token Index: 782