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

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

Neuron 2315 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.8638. Min Act: -0.0002

Data Index: 1356696 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.8174. Min Act: -0.0002

Data Index: 696243 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7240. Min Act: -0.0002

Data Index: 1310698 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7980. Min Act: -0.0002

Data Index: 224948 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.8062. Min Act: -0.0002

Data Index: 758977 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7490. Min Act: -0.0002

Data Index: 949226 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6825. Min Act: -0.0002

Data Index: 286092 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6049. Min Act: -0.0002

Data Index: 785622 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6948. Min Act: -0.0002

Data Index: 1563636 (Python Code)

Max Activating Token Index: 774

Text #9

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7094. Min Act: -0.0002

Data Index: 1396215 (Python Code)

Max Activating Token Index: 942

Text #10

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6448. Min Act: -0.0002

Data Index: 1237970 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6239. Min Act: -0.0002

Data Index: 946554 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6853. Min Act: -0.0002

Data Index: 720028 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6250. Min Act: -0.0002

Data Index: 1072968 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6667. Min Act: -0.0002

Data Index: 788912 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6910. Min Act: -0.0002

Data Index: 357103 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6050. Min Act: -0.0002

Data Index: 945111 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.5945. Min Act: -0.0002

Data Index: 993189 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6896. Min Act: -0.0002

Data Index: 1134723 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.5030. Min Act: -0.0002

Data Index: 1340488 (C4 (Web Text))

Max Activating Token Index: 729