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

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

Neuron 3084 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4200. Min Range: -3.4200

Max Act: 3.4200. Min Act: -0.0001

Data Index: 1351115 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 3.4200. Min Range: -3.4200

Max Act: 3.2821. Min Act: -0.0001

Data Index: 447263 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.9945. Min Act: -0.0001

Data Index: 605053 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.8240. Min Act: -0.0000

Data Index: 210085 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.9491. Min Act: -0.0001

Data Index: 1273905 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.9514. Min Act: -0.0000

Data Index: 685380 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.8679. Min Act: -0.0001

Data Index: 980834 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.8169. Min Act: -0.0001

Data Index: 109785 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.2055. Min Act: -0.0001

Data Index: 920375 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.2939. Min Act: -0.0001

Data Index: 656528 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.3629. Min Act: -0.0000

Data Index: 970247 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.3344. Min Act: -0.0000

Data Index: 1086029 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.1234. Min Act: -0.0001

Data Index: 214137 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.4472. Min Act: -0.0001

Data Index: 780801 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.2070. Min Act: -0.0001

Data Index: 1121670 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.1397. Min Act: -0.0001

Data Index: 989027 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.1466. Min Act: -0.0001

Data Index: 756956 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.0155. Min Act: -0.0001

Data Index: 876185 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.1270. Min Act: -0.0000

Data Index: 90638 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.0737. Min Act: -0.0001

Data Index: 202483 (C4 (Web Text))

Max Activating Token Index: 168