Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5886 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.5080. Min Range: -4.5080

Max Act: 4.5080. Min Act: -0.0000

Data Index: 1402681 (Python Code)

Max Activating Token Index: 309

Text #1

Max Range: 4.5080. Min Range: -4.5080

Max Act: 3.6502. Min Act: -0.0000

Data Index: 1405754 (Python Code)

Max Activating Token Index: 204

Text #2

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.8540. Min Act: -0.0000

Data Index: 1518842 (Python Code)

Max Activating Token Index: 970

Text #3

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.4892. Min Act: -0.0000

Data Index: 1375101 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.4315. Min Act: -0.0000

Data Index: 1302608 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.8612. Min Act: -0.0000

Data Index: 1602261 (Python Code)

Max Activating Token Index: 862

Text #6

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.2815. Min Act: -0.0000

Data Index: 1606636 (Python Code)

Max Activating Token Index: 399

Text #7

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.6883. Min Act: -0.0000

Data Index: 1528276 (Python Code)

Max Activating Token Index: 872

Text #8

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.3932. Min Act: -0.0000

Data Index: 80861 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.4015. Min Act: -0.0000

Data Index: 1448860 (Python Code)

Max Activating Token Index: 885

Text #10

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.2939. Min Act: -0.0000

Data Index: 363077 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.3078. Min Act: -0.0000

Data Index: 1647879 (Python Code)

Max Activating Token Index: 100

Text #12

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.2684. Min Act: -0.0000

Data Index: 116743 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.4004. Min Act: -0.0000

Data Index: 553253 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.2479. Min Act: -0.0000

Data Index: 1442533 (Python Code)

Max Activating Token Index: 623

Text #15

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.1898. Min Act: -0.0000

Data Index: 1416849 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 4.5080. Min Range: -4.5080

Max Act: 2.3309. Min Act: -0.0000

Data Index: 917621 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 4.5080. Min Range: -4.5080

Max Act: 1.9549. Min Act: -0.0000

Data Index: 1533340 (Python Code)

Max Activating Token Index: 1009

Text #18

Max Range: 4.5080. Min Range: -4.5080

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1409099 (Python Code)

Max Activating Token Index: 307

Text #19

Max Range: 4.5080. Min Range: -4.5080

Max Act: 1.5923. Min Act: -0.0000

Data Index: 1617658 (Python Code)

Max Activating Token Index: 507