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

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

Neuron 2871 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.4039. Min Act: -0.0000

Data Index: 1642958 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.2688. Min Act: -0.0001

Data Index: 1432459 (Python Code)

Max Activating Token Index: 466

Text #2

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.1222. Min Act: -0.0001

Data Index: 1640462 (Python Code)

Max Activating Token Index: 609

Text #3

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.1006. Min Act: -0.0001

Data Index: 1369093 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.0538. Min Act: -0.0001

Data Index: 1550673 (Python Code)

Max Activating Token Index: 297

Text #5

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.0129. Min Act: -0.0001

Data Index: 1478832 (Python Code)

Max Activating Token Index: 336

Text #6

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.1653. Min Act: -0.0001

Data Index: 1403913 (Python Code)

Max Activating Token Index: 705

Text #7

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.0059. Min Act: -0.0001

Data Index: 1439199 (Python Code)

Max Activating Token Index: 972

Text #8

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.9781. Min Act: -0.0001

Data Index: 1536022 (Python Code)

Max Activating Token Index: 114

Text #9

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.9776. Min Act: -0.0001

Data Index: 1420087 (Python Code)

Max Activating Token Index: 900

Text #10

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.9665. Min Act: -0.0001

Data Index: 1610953 (Python Code)

Max Activating Token Index: 927

Text #11

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.9223. Min Act: -0.0000

Data Index: 1420318 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.8002. Min Act: -0.0001

Data Index: 1435915 (Python Code)

Max Activating Token Index: 197

Text #13

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.9237. Min Act: -0.0001

Data Index: 1564524 (Python Code)

Max Activating Token Index: 688

Text #14

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.9124. Min Act: -0.0001

Data Index: 1512879 (Python Code)

Max Activating Token Index: 562

Text #15

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.9073. Min Act: -0.0000

Data Index: 1550175 (Python Code)

Max Activating Token Index: 436

Text #16

Max Range: 3.4039. Min Range: -3.4039

Max Act: 2.8992. Min Act: -0.0000

Data Index: 1380835 (Python Code)

Max Activating Token Index: 173

Text #17

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.0427. Min Act: -0.0001

Data Index: 1391847 (Python Code)

Max Activating Token Index: 882

Text #18

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.0327. Min Act: -0.0001

Data Index: 1453771 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 3.4039. Min Range: -3.4039

Max Act: 3.0095. Min Act: -0.0001

Data Index: 1495130 (Python Code)

Max Activating Token Index: 635