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

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

Neuron 1598 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1801. Min Range: -1.1801

Max Act: 1.1801. Min Act: -0.0001

Data Index: 1525147 (Python Code)

Max Activating Token Index: 364

Text #1

Max Range: 1.1801. Min Range: -1.1801

Max Act: 1.0260. Min Act: -0.0001

Data Index: 1495869 (Python Code)

Max Activating Token Index: 473

Text #2

Max Range: 1.1801. Min Range: -1.1801

Max Act: 1.0943. Min Act: -0.0001

Data Index: 1429173 (Python Code)

Max Activating Token Index: 451

Text #3

Max Range: 1.1801. Min Range: -1.1801

Max Act: 1.1377. Min Act: -0.0001

Data Index: 1531949 (Python Code)

Max Activating Token Index: 360

Text #4

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.9866. Min Act: -0.0001

Data Index: 1366372 (Python Code)

Max Activating Token Index: 164

Text #5

Max Range: 1.1801. Min Range: -1.1801

Max Act: 1.0118. Min Act: -0.0001

Data Index: 1439903 (Python Code)

Max Activating Token Index: 682

Text #6

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.9870. Min Act: -0.0001

Data Index: 1554565 (Python Code)

Max Activating Token Index: 419

Text #7

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.9528. Min Act: -0.0001

Data Index: 1449789 (Python Code)

Max Activating Token Index: 613

Text #8

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.9071. Min Act: -0.0001

Data Index: 1375053 (Python Code)

Max Activating Token Index: 136

Text #9

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8829. Min Act: -0.0001

Data Index: 1374230 (Python Code)

Max Activating Token Index: 507

Text #10

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8997. Min Act: -0.0001

Data Index: 1254665 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.9529. Min Act: -0.0001

Data Index: 487768 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8470. Min Act: -0.0001

Data Index: 1564193 (Python Code)

Max Activating Token Index: 123

Text #13

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.9166. Min Act: -0.0001

Data Index: 1011252 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8613. Min Act: -0.0001

Data Index: 1629397 (Python Code)

Max Activating Token Index: 45

Text #15

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8587. Min Act: -0.0001

Data Index: 640768 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.9048. Min Act: -0.0001

Data Index: 347674 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8698. Min Act: -0.0001

Data Index: 2105 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8679. Min Act: -0.0001

Data Index: 17671 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8152. Min Act: -0.0001

Data Index: 86590 (C4 (Web Text))

Max Activating Token Index: 612