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

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

Neuron 5954 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1131. Min Range: -4.1131

Max Act: 4.1131. Min Act: -0.0000

Data Index: 1380451 (Python Code)

Max Activating Token Index: 305

Text #1

Max Range: 4.1131. Min Range: -4.1131

Max Act: 3.3365. Min Act: -0.0000

Data Index: 1387169 (Python Code)

Max Activating Token Index: 1015

Text #2

Max Range: 4.1131. Min Range: -4.1131

Max Act: 2.6563. Min Act: 0.0000

Data Index: 1592277 (Python Code)

Max Activating Token Index: 593

Text #3

Max Range: 4.1131. Min Range: -4.1131

Max Act: 2.4372. Min Act: -0.0000

Data Index: 54857 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.8815. Min Act: -0.0000

Data Index: 1613775 (Python Code)

Max Activating Token Index: 517

Text #5

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.8533. Min Act: -0.0000

Data Index: 1348646 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.9137. Min Act: -0.0000

Data Index: 1534548 (Python Code)

Max Activating Token Index: 507

Text #7

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.7895. Min Act: -0.0000

Data Index: 1455984 (Python Code)

Max Activating Token Index: 324

Text #8

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.5160. Min Act: -0.0000

Data Index: 1197877 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.5888. Min Act: -0.0000

Data Index: 1055564 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.5847. Min Act: -0.0000

Data Index: 1075288 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.4786. Min Act: -0.0000

Data Index: 1165677 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.4502. Min Act: -0.0000

Data Index: 1099467 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.5116. Min Act: -0.0000

Data Index: 1489471 (Python Code)

Max Activating Token Index: 445

Text #14

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.5362. Min Act: -0.0000

Data Index: 1585259 (Python Code)

Max Activating Token Index: 919

Text #15

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.4039. Min Act: -0.0000

Data Index: 1193980 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.3653. Min Act: -0.0000

Data Index: 707174 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.2645. Min Act: -0.0000

Data Index: 1399852 (Python Code)

Max Activating Token Index: 633

Text #18

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.3271. Min Act: -0.0000

Data Index: 1438453 (Python Code)

Max Activating Token Index: 975

Text #19

Max Range: 4.1131. Min Range: -4.1131

Max Act: 1.2452. Min Act: -0.0000

Data Index: 431783 (C4 (Web Text))

Max Activating Token Index: 985