Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1490 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.1714. Min Range: -5.1714

Max Act: 5.1714. Min Act: -0.1700

Data Index: 1467669 (Python Code)

Max Activating Token Index: 504

Text #1

Max Range: 5.1714. Min Range: -5.1714

Max Act: 5.1714. Min Act: -0.1700

Data Index: 1432221 (Python Code)

Max Activating Token Index: 222

Text #2

Max Range: 5.1714. Min Range: -5.1714

Max Act: 5.1714. Min Act: -0.1700

Data Index: 1500258 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 5.1714. Min Range: -5.1714

Max Act: 5.0152. Min Act: -0.1700

Data Index: 1444257 (Python Code)

Max Activating Token Index: 820

Text #4

Max Range: 5.1714. Min Range: -5.1714

Max Act: 5.0777. Min Act: -0.1700

Data Index: 1545567 (Python Code)

Max Activating Token Index: 121

Text #5

Max Range: 5.1714. Min Range: -5.1714

Max Act: 4.9214. Min Act: -0.1700

Data Index: 1478564 (Python Code)

Max Activating Token Index: 408

Text #6

Max Range: 5.1714. Min Range: -5.1714

Max Act: 5.1089. Min Act: -0.1700

Data Index: 1371891 (Python Code)

Max Activating Token Index: 338

Text #7

Max Range: 5.1714. Min Range: -5.1714

Max Act: 5.0777. Min Act: -0.1700

Data Index: 1448743 (Python Code)

Max Activating Token Index: 414

Text #8

Max Range: 5.1714. Min Range: -5.1714

Max Act: 4.9839. Min Act: -0.1700

Data Index: 1564470 (Python Code)

Max Activating Token Index: 559

Text #9

Max Range: 5.1714. Min Range: -5.1714

Max Act: 5.0152. Min Act: -0.1700

Data Index: 1652435 (Python Code)

Max Activating Token Index: 345

Text #10

Max Range: 5.1714. Min Range: -5.1714

Max Act: 5.1402. Min Act: -0.1699

Data Index: 1592214 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 5.1714. Min Range: -5.1714

Max Act: 4.9839. Min Act: -0.1700

Data Index: 1640069 (Python Code)

Max Activating Token Index: 304

Text #12

Max Range: 5.1714. Min Range: -5.1714

Max Act: 4.9527. Min Act: -0.1700

Data Index: 1402587 (Python Code)

Max Activating Token Index: 423

Text #13

Max Range: 5.1714. Min Range: -5.1714

Max Act: 4.9839. Min Act: -0.1700

Data Index: 1442794 (Python Code)

Max Activating Token Index: 616

Text #14

Max Range: 5.1714. Min Range: -5.1714

Max Act: 4.9839. Min Act: -0.1700

Data Index: 1565842 (Python Code)

Max Activating Token Index: 420

Text #15

Max Range: 5.1714. Min Range: -5.1714

Max Act: 4.9527. Min Act: -0.1700

Data Index: 1421986 (Python Code)

Max Activating Token Index: 781

Text #16

Max Range: 5.1714. Min Range: -5.1714

Max Act: 4.8902. Min Act: -0.1700

Data Index: 1414905 (Python Code)

Max Activating Token Index: 717

Text #17

Max Range: 5.1714. Min Range: -5.1714

Max Act: 4.9839. Min Act: -0.1700

Data Index: 1606717 (Python Code)

Max Activating Token Index: 136

Text #18

Max Range: 5.1714. Min Range: -5.1714

Max Act: 5.0152. Min Act: -0.1700

Data Index: 1457741 (Python Code)

Max Activating Token Index: 391

Text #19

Max Range: 5.1714. Min Range: -5.1714

Max Act: 4.9214. Min Act: -0.1700

Data Index: 1566225 (Python Code)

Max Activating Token Index: 318