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

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

Neuron 430 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.5949. Min Act: -0.0004

Data Index: 1618123 (Python Code)

Max Activating Token Index: 233

Text #1

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.5894. Min Act: -0.0004

Data Index: 1614223 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.7576. Min Act: -0.0004

Data Index: 1554485 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.6101. Min Act: -0.0004

Data Index: 1639248 (Python Code)

Max Activating Token Index: 1003

Text #4

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.6816. Min Act: -0.0004

Data Index: 1455023 (Python Code)

Max Activating Token Index: 988

Text #5

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.3789. Min Act: -0.0004

Data Index: 1423147 (Python Code)

Max Activating Token Index: 547

Text #6

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.4174. Min Act: -0.0004

Data Index: 1600261 (Python Code)

Max Activating Token Index: 221

Text #7

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.1717. Min Act: -0.0004

Data Index: 1550482 (Python Code)

Max Activating Token Index: 561

Text #8

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.3237. Min Act: -0.0004

Data Index: 1370974 (Python Code)

Max Activating Token Index: 286

Text #9

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.0786. Min Act: -0.0004

Data Index: 867527 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.3382. Min Act: -0.0004

Data Index: 1574742 (Python Code)

Max Activating Token Index: 74

Text #11

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.1235. Min Act: -0.0004

Data Index: 1524180 (Python Code)

Max Activating Token Index: 292

Text #12

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.4826. Min Act: -0.0004

Data Index: 1485167 (Python Code)

Max Activating Token Index: 240

Text #13

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.2843. Min Act: -0.0004

Data Index: 1511620 (Python Code)

Max Activating Token Index: 905

Text #14

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.4326. Min Act: -0.0004

Data Index: 1386199 (Python Code)

Max Activating Token Index: 77

Text #15

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.1646. Min Act: -0.0004

Data Index: 1649000 (Python Code)

Max Activating Token Index: 522

Text #16

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.3006. Min Act: -0.0004

Data Index: 1553687 (Python Code)

Max Activating Token Index: 586

Text #17

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.1630. Min Act: -0.0004

Data Index: 1567621 (Python Code)

Max Activating Token Index: 633

Text #18

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.4082. Min Act: -0.0004

Data Index: 1363749 (Python Code)

Max Activating Token Index: 1012

Text #19

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.4043. Min Act: -0.0004

Data Index: 1535117 (Python Code)

Max Activating Token Index: 151