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

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

Neuron 2524 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.5338. Min Act: -0.0000

Data Index: 16821 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.5048. Min Act: -0.0000

Data Index: 388211 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4732. Min Act: -0.0000

Data Index: 748436 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4622. Min Act: -0.0000

Data Index: 666400 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4725. Min Act: -0.0000

Data Index: 104111 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4299. Min Act: -0.0000

Data Index: 1097061 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4172. Min Act: -0.0000

Data Index: 306626 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4416. Min Act: -0.0000

Data Index: 298061 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1142512 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4967. Min Act: -0.0000

Data Index: 913385 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4073. Min Act: -0.0000

Data Index: 729774 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1166411 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1191824 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1321640 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4078. Min Act: -0.0000

Data Index: 239344 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4092. Min Act: -0.0000

Data Index: 721474 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3710. Min Act: -0.0000

Data Index: 702835 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3914. Min Act: -0.0000

Data Index: 424035 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3838. Min Act: -0.0000

Data Index: 753492 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3602. Min Act: -0.0000

Data Index: 517523 (C4 (Web Text))

Max Activating Token Index: 908