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

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

Neuron 2787 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2378. Min Act: -0.0001

Data Index: 684102 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1396025 (Python Code)

Max Activating Token Index: 921

Text #2

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1518410 (Python Code)

Max Activating Token Index: 964

Text #3

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2117. Min Act: -0.0001

Data Index: 254841 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2068. Min Act: -0.0001

Data Index: 726096 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1917. Min Act: -0.0001

Data Index: 141648 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1649. Min Act: -0.0001

Data Index: 12737 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1988. Min Act: -0.0001

Data Index: 478685 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1912. Min Act: -0.0001

Data Index: 56141 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1956. Min Act: -0.0001

Data Index: 339813 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1794. Min Act: -0.0001

Data Index: 1261564 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1792. Min Act: -0.0001

Data Index: 61177 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1932. Min Act: -0.0001

Data Index: 371402 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1846. Min Act: -0.0001

Data Index: 1638103 (Python Code)

Max Activating Token Index: 891

Text #14

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2044. Min Act: -0.0001

Data Index: 56274 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1770. Min Act: -0.0001

Data Index: 336038 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1694. Min Act: -0.0001

Data Index: 78059 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1885. Min Act: -0.0001

Data Index: 1412080 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1724. Min Act: -0.0001

Data Index: 1576262 (Python Code)

Max Activating Token Index: 271

Text #19

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.1806. Min Act: -0.0001

Data Index: 13984 (C4 (Web Text))

Max Activating Token Index: 430