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

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

Neuron 4278 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: 1.0068. Min Range: -1.0068

Max Act: 1.0068. Min Act: -0.0000

Data Index: 1623935 (Python Code)

Max Activating Token Index: 933

Text #1

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1428443 (Python Code)

Max Activating Token Index: 882

Text #2

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.9855. Min Act: -0.0000

Data Index: 1564421 (Python Code)

Max Activating Token Index: 867

Text #3

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1503049 (Python Code)

Max Activating Token Index: 578

Text #4

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1738 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1441710 (Python Code)

Max Activating Token Index: 622

Text #6

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1619035 (Python Code)

Max Activating Token Index: 798

Text #7

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7344. Min Act: -0.0000

Data Index: 146077 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1654161 (Python Code)

Max Activating Token Index: 91

Text #9

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1502564 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1540237 (Python Code)

Max Activating Token Index: 172

Text #11

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1445569 (Python Code)

Max Activating Token Index: 720

Text #12

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1461558 (Python Code)

Max Activating Token Index: 882

Text #13

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1607486 (Python Code)

Max Activating Token Index: 580

Text #14

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1655005 (Python Code)

Max Activating Token Index: 431

Text #15

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1533416 (Python Code)

Max Activating Token Index: 313

Text #16

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1420125 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1511716 (Python Code)

Max Activating Token Index: 895

Text #18

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1491804 (Python Code)

Max Activating Token Index: 1022

Text #19

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6660. Min Act: -0.0000

Data Index: 207452 (C4 (Web Text))

Max Activating Token Index: 680