Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2188 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.1215. Min Act: -0.0001

Data Index: 544368 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1222718 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1572312 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0845. Min Act: -0.0000

Data Index: 680759 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0942. Min Act: -0.0001

Data Index: 445102 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0756. Min Act: -0.0000

Data Index: 1370845 (Python Code)

Max Activating Token Index: 984

Text #6

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1457588 (Python Code)

Max Activating Token Index: 351

Text #7

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1640270 (Python Code)

Max Activating Token Index: 641

Text #8

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0973. Min Act: -0.0001

Data Index: 819225 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0783. Min Act: -0.0000

Data Index: 59443 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1481501 (Python Code)

Max Activating Token Index: 392

Text #11

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0809. Min Act: -0.0000

Data Index: 765893 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1349654 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0832. Min Act: -0.0000

Data Index: 429376 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0887. Min Act: -0.0001

Data Index: 815696 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0842. Min Act: -0.0001

Data Index: 492611 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1613335 (Python Code)

Max Activating Token Index: 859

Text #17

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0783. Min Act: -0.0000

Data Index: 85481 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1434776 (Python Code)

Max Activating Token Index: 314

Text #19

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1154116 (C4 (Web Text))

Max Activating Token Index: 982