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

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

Neuron 4638 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3749. Min Range: -7.3749

Max Act: 7.3749. Min Act: -0.0000

Data Index: 1656057 (Python Code)

Max Activating Token Index: 362

Text #1

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.3419. Min Act: -0.0000

Data Index: 1363488 (Python Code)

Max Activating Token Index: 112

Text #2

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.9139. Min Act: -0.0000

Data Index: 1360679 (Python Code)

Max Activating Token Index: 706

Text #3

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.4185. Min Act: -0.0000

Data Index: 1581224 (Python Code)

Max Activating Token Index: 1008

Text #4

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.6049. Min Act: -0.0000

Data Index: 1524458 (Python Code)

Max Activating Token Index: 974

Text #5

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.5643. Min Act: -0.0000

Data Index: 1626094 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.9737. Min Act: -0.0000

Data Index: 1510065 (Python Code)

Max Activating Token Index: 636

Text #7

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.8429. Min Act: -0.0000

Data Index: 1457219 (Python Code)

Max Activating Token Index: 118

Text #8

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.2741. Min Act: -0.0000

Data Index: 1559897 (Python Code)

Max Activating Token Index: 269

Text #9

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.5857. Min Act: -0.0000

Data Index: 1421687 (Python Code)

Max Activating Token Index: 273

Text #10

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.4064. Min Act: -0.0000

Data Index: 1375010 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.3132. Min Act: -0.0000

Data Index: 1370982 (Python Code)

Max Activating Token Index: 712

Text #12

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.2799. Min Act: -0.0000

Data Index: 1391795 (Python Code)

Max Activating Token Index: 1011

Text #13

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.0150. Min Act: -0.0000

Data Index: 1548474 (Python Code)

Max Activating Token Index: 495

Text #14

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.2338. Min Act: -0.0000

Data Index: 1476995 (Python Code)

Max Activating Token Index: 139

Text #15

Max Range: 7.3749. Min Range: -7.3749

Max Act: 5.9832. Min Act: -0.0000

Data Index: 1492037 (Python Code)

Max Activating Token Index: 489

Text #16

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.3582. Min Act: -0.0000

Data Index: 1565022 (Python Code)

Max Activating Token Index: 594

Text #17

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.1258. Min Act: -0.0000

Data Index: 1518006 (Python Code)

Max Activating Token Index: 932

Text #18

Max Range: 7.3749. Min Range: -7.3749

Max Act: 6.2821. Min Act: -0.0000

Data Index: 1630167 (Python Code)

Max Activating Token Index: 206

Text #19

Max Range: 7.3749. Min Range: -7.3749

Max Act: 5.9204. Min Act: -0.0000

Data Index: 1426189 (Python Code)

Max Activating Token Index: 683