Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 687 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3157. Min Act: -0.0002

Data Index: 1429936 (Python Code)

Max Activating Token Index: 891

Text #1

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3554. Min Act: -0.0003

Data Index: 1119452 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3456. Min Act: -0.0003

Data Index: 909096 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3130. Min Act: -0.0003

Data Index: 1582606 (Python Code)

Max Activating Token Index: 905

Text #4

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3159. Min Act: -0.0003

Data Index: 1379654 (Python Code)

Max Activating Token Index: 846

Text #5

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2530. Min Act: -0.0003

Data Index: 1656374 (Python Code)

Max Activating Token Index: 912

Text #6

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2671. Min Act: -0.0003

Data Index: 260923 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3081. Min Act: -0.0002

Data Index: 1554253 (Python Code)

Max Activating Token Index: 644

Text #8

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2927. Min Act: -0.0002

Data Index: 1361403 (Python Code)

Max Activating Token Index: 849

Text #9

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2927. Min Act: -0.0002

Data Index: 1473083 (Python Code)

Max Activating Token Index: 1001

Text #10

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3021. Min Act: -0.0003

Data Index: 1567833 (Python Code)

Max Activating Token Index: 743

Text #11

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3000. Min Act: -0.0002

Data Index: 1654787 (Python Code)

Max Activating Token Index: 756

Text #12

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2996. Min Act: -0.0002

Data Index: 1443718 (Python Code)

Max Activating Token Index: 994

Text #13

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2768. Min Act: -0.0002

Data Index: 1528500 (Python Code)

Max Activating Token Index: 265

Text #14

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3370. Min Act: -0.0002

Data Index: 1458227 (Python Code)

Max Activating Token Index: 971

Text #15

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3050. Min Act: -0.0003

Data Index: 1656880 (Python Code)

Max Activating Token Index: 931

Text #16

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2841. Min Act: -0.0002

Data Index: 1469376 (Python Code)

Max Activating Token Index: 518

Text #17

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3045. Min Act: -0.0002

Data Index: 1648033 (Python Code)

Max Activating Token Index: 1012

Text #18

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2901. Min Act: -0.0003

Data Index: 1313977 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2607. Min Act: -0.0003

Data Index: 1157349 (C4 (Web Text))

Max Activating Token Index: 513