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

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

Neuron 4403 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: 4.3804. Min Range: -4.3804

Max Act: 4.3804. Min Act: -0.0001

Data Index: 951678 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 4.3804. Min Range: -4.3804

Max Act: 3.7249. Min Act: -0.0000

Data Index: 1151315 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.9399. Min Act: -0.0000

Data Index: 170905 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.7721. Min Act: -0.0000

Data Index: 1086211 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.7719. Min Act: -0.0000

Data Index: 614706 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.9200. Min Act: -0.0001

Data Index: 38188 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.5237. Min Act: -0.0000

Data Index: 159941 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.6092. Min Act: -0.0000

Data Index: 1162888 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.5880. Min Act: -0.0000

Data Index: 719468 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.6350. Min Act: -0.0000

Data Index: 746000 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.8161. Min Act: -0.0000

Data Index: 774409 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.2604. Min Act: -0.0000

Data Index: 1046677 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.6535. Min Act: -0.0000

Data Index: 1246422 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.4835. Min Act: -0.0000

Data Index: 977830 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.3925. Min Act: -0.0000

Data Index: 1096733 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.5652. Min Act: -0.0000

Data Index: 444409 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.3048. Min Act: -0.0000

Data Index: 665289 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.4964. Min Act: -0.0000

Data Index: 1013671 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.4813. Min Act: -0.0000

Data Index: 332940 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 4.3804. Min Range: -4.3804

Max Act: 2.4913. Min Act: -0.0000

Data Index: 1233491 (C4 (Web Text))

Max Activating Token Index: 189