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

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

Neuron 3642 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.9410. Min Act: -0.0001

Data Index: 1086307 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.8945. Min Act: -0.0001

Data Index: 1330907 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.6928. Min Act: -0.0001

Data Index: 142351 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.7095. Min Act: -0.0001

Data Index: 757811 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.7723. Min Act: -0.0001

Data Index: 804662 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.7294. Min Act: -0.0001

Data Index: 954591 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.7183. Min Act: -0.0001

Data Index: 1075956 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4713. Min Act: -0.0001

Data Index: 529733 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4750. Min Act: -0.0001

Data Index: 856375 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.5615. Min Act: -0.0001

Data Index: 1320444 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.5295. Min Act: -0.0001

Data Index: 228256 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.5024. Min Act: -0.0001

Data Index: 1039709 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4755. Min Act: -0.0001

Data Index: 1062303 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4804. Min Act: -0.0001

Data Index: 1406749 (Python Code)

Max Activating Token Index: 106

Text #14

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3217. Min Act: -0.0001

Data Index: 658472 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4010. Min Act: -0.0001

Data Index: 53098 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4970. Min Act: -0.0001

Data Index: 489426 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3562. Min Act: -0.0001

Data Index: 1291107 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4089. Min Act: -0.0001

Data Index: 1082080 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3301. Min Act: -0.0001

Data Index: 281880 (C4 (Web Text))

Max Activating Token Index: 918