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

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

Neuron 1211 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: 2.3944. Min Range: -2.3944

Max Act: 2.3944. Min Act: -0.0000

Data Index: 1338209 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.8381. Min Act: -0.0000

Data Index: 896421 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.6766. Min Act: -0.0000

Data Index: 1354772 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.6462. Min Act: -0.0000

Data Index: 627078 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.6279. Min Act: -0.0000

Data Index: 1205553 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.6049. Min Act: -0.0000

Data Index: 570692 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.5877. Min Act: -0.0000

Data Index: 1008165 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.5724. Min Act: -0.0000

Data Index: 1173933 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.4758. Min Act: -0.0000

Data Index: 1351164 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.3481. Min Act: -0.0000

Data Index: 211926 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.3984. Min Act: -0.0000

Data Index: 1308424 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.3846. Min Act: -0.0000

Data Index: 1175957 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.3903. Min Act: -0.0000

Data Index: 1341001 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.4591. Min Act: -0.0000

Data Index: 1140868 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1485085 (Python Code)

Max Activating Token Index: 332

Text #15

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.4485. Min Act: -0.0000

Data Index: 176144 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.2159. Min Act: -0.0000

Data Index: 523808 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.2824. Min Act: -0.0000

Data Index: 1458455 (Python Code)

Max Activating Token Index: 257

Text #18

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.2567. Min Act: -0.0000

Data Index: 584162 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 2.3944. Min Range: -2.3944

Max Act: 1.3440. Min Act: -0.0000

Data Index: 719629 (C4 (Web Text))

Max Activating Token Index: 312