Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2137 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.7806. Min Act: -0.0001

Data Index: 1386820 (Python Code)

Max Activating Token Index: 818

Text #1

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.7083. Min Act: -0.0001

Data Index: 1461987 (Python Code)

Max Activating Token Index: 61

Text #2

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.7083. Min Act: -0.0001

Data Index: 1459151 (Python Code)

Max Activating Token Index: 622

Text #3

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6624. Min Act: -0.0001

Data Index: 1380221 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6465. Min Act: -0.0001

Data Index: 1443722 (Python Code)

Max Activating Token Index: 220

Text #5

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6798. Min Act: -0.0001

Data Index: 1494921 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.7200. Min Act: -0.0001

Data Index: 1553022 (Python Code)

Max Activating Token Index: 152

Text #7

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.7345. Min Act: -0.0001

Data Index: 1487018 (Python Code)

Max Activating Token Index: 373

Text #8

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5817. Min Act: -0.0001

Data Index: 1513665 (Python Code)

Max Activating Token Index: 816

Text #9

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.7299. Min Act: -0.0001

Data Index: 1362868 (Python Code)

Max Activating Token Index: 938

Text #10

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5683. Min Act: -0.0001

Data Index: 1363109 (Python Code)

Max Activating Token Index: 295

Text #11

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6616. Min Act: -0.0002

Data Index: 1444915 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.7039. Min Act: -0.0001

Data Index: 1455969 (Python Code)

Max Activating Token Index: 122

Text #13

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6565. Min Act: -0.0001

Data Index: 1450457 (Python Code)

Max Activating Token Index: 61

Text #14

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6119. Min Act: -0.0001

Data Index: 1418923 (Python Code)

Max Activating Token Index: 118

Text #15

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6043. Min Act: -0.0001

Data Index: 1468284 (Python Code)

Max Activating Token Index: 40

Text #16

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6005. Min Act: -0.0001

Data Index: 1536831 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6152. Min Act: -0.0001

Data Index: 1386907 (Python Code)

Max Activating Token Index: 591

Text #18

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6573. Min Act: -0.0001

Data Index: 1537644 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6387. Min Act: -0.0001

Data Index: 1362566 (Python Code)

Max Activating Token Index: 27