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

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

Neuron 5572 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: 5.7943. Min Range: -5.7943

Max Act: 5.7943. Min Act: -0.0000

Data Index: 792633 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 5.7943. Min Range: -5.7943

Max Act: 5.3199. Min Act: -0.0000

Data Index: 842967 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 5.7943. Min Range: -5.7943

Max Act: 5.1993. Min Act: -0.0000

Data Index: 581528 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.8446. Min Act: -0.0000

Data Index: 1220288 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.8935. Min Act: -0.0000

Data Index: 124174 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.7004. Min Act: -0.0000

Data Index: 1048159 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.6051. Min Act: -0.0000

Data Index: 723288 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.2191. Min Act: -0.0000

Data Index: 524135 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.4768. Min Act: -0.0000

Data Index: 762567 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.4107. Min Act: -0.0000

Data Index: 1078772 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.5399. Min Act: -0.0000

Data Index: 267304 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.5116. Min Act: -0.0000

Data Index: 98915 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.4975. Min Act: -0.0000

Data Index: 816318 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.1062. Min Act: -0.0000

Data Index: 789329 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.5981. Min Act: -0.0000

Data Index: 106735 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.2237. Min Act: -0.0000

Data Index: 1058176 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 5.7943. Min Range: -5.7943

Max Act: 3.8568. Min Act: -0.0000

Data Index: 783012 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 5.7943. Min Range: -5.7943

Max Act: 4.1763. Min Act: -0.0000

Data Index: 620793 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 5.7943. Min Range: -5.7943

Max Act: 3.8354. Min Act: -0.0000

Data Index: 395969 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 5.7943. Min Range: -5.7943

Max Act: 3.8008. Min Act: -0.0000

Data Index: 164190 (C4 (Web Text))

Max Activating Token Index: 992