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

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

Neuron 1996 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.9619. Min Act: -0.0001

Data Index: 1533123 (Python Code)

Max Activating Token Index: 270

Text #1

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.9555. Min Act: -0.0001

Data Index: 1627221 (Python Code)

Max Activating Token Index: 46

Text #2

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.8092. Min Act: -0.0001

Data Index: 1569421 (Python Code)

Max Activating Token Index: 621

Text #3

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.8188. Min Act: -0.0001

Data Index: 1587006 (Python Code)

Max Activating Token Index: 767

Text #4

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.7608. Min Act: -0.0001

Data Index: 1652031 (Python Code)

Max Activating Token Index: 530

Text #5

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.7857. Min Act: -0.0001

Data Index: 1563405 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.7473. Min Act: -0.0001

Data Index: 1469144 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.7292. Min Act: -0.0001

Data Index: 1522169 (Python Code)

Max Activating Token Index: 151

Text #8

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.7257. Min Act: -0.0001

Data Index: 1465114 (Python Code)

Max Activating Token Index: 173

Text #9

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.6961. Min Act: -0.0001

Data Index: 1496069 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.7252. Min Act: -0.0001

Data Index: 1525176 (Python Code)

Max Activating Token Index: 472

Text #11

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.6872. Min Act: -0.0001

Data Index: 1451313 (Python Code)

Max Activating Token Index: 70

Text #12

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.6940. Min Act: -0.0001

Data Index: 1463215 (Python Code)

Max Activating Token Index: 439

Text #13

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.7158. Min Act: -0.0001

Data Index: 315515 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.6686. Min Act: -0.0001

Data Index: 1455607 (Python Code)

Max Activating Token Index: 51

Text #15

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.6413. Min Act: -0.0001

Data Index: 1393822 (Python Code)

Max Activating Token Index: 294

Text #16

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.6604. Min Act: -0.0001

Data Index: 1558792 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.6596. Min Act: -0.0001

Data Index: 1445930 (Python Code)

Max Activating Token Index: 964

Text #18

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.6790. Min Act: -0.0001

Data Index: 1401621 (Python Code)

Max Activating Token Index: 205

Text #19

Max Range: 0.9619. Min Range: -0.9619

Max Act: 0.6780. Min Act: -0.0001

Data Index: 1417778 (Python Code)

Max Activating Token Index: 452