Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 419 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.2907. Min Range: -7.2907

Max Act: 7.2907. Min Act: -0.1700

Data Index: 1502271 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 7.2907. Min Range: -7.2907

Max Act: 7.1657. Min Act: -0.1700

Data Index: 1364919 (Python Code)

Max Activating Token Index: 921

Text #2

Max Range: 7.2907. Min Range: -7.2907

Max Act: 7.1657. Min Act: -0.1700

Data Index: 1428404 (Python Code)

Max Activating Token Index: 802

Text #3

Max Range: 7.2907. Min Range: -7.2907

Max Act: 7.1657. Min Act: -0.1700

Data Index: 1393801 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 7.2907. Min Range: -7.2907

Max Act: 7.1032. Min Act: -0.1700

Data Index: 1362467 (Python Code)

Max Activating Token Index: 951

Text #5

Max Range: 7.2907. Min Range: -7.2907

Max Act: 7.1032. Min Act: -0.1700

Data Index: 1513189 (Python Code)

Max Activating Token Index: 921

Text #6

Max Range: 7.2907. Min Range: -7.2907

Max Act: 6.9782. Min Act: -0.1700

Data Index: 1508778 (Python Code)

Max Activating Token Index: 811

Text #7

Max Range: 7.2907. Min Range: -7.2907

Max Act: 7.0407. Min Act: -0.1700

Data Index: 1505606 (Python Code)

Max Activating Token Index: 286

Text #8

Max Range: 7.2907. Min Range: -7.2907

Max Act: 6.9157. Min Act: -0.1700

Data Index: 1632532 (Python Code)

Max Activating Token Index: 860

Text #9

Max Range: 7.2907. Min Range: -7.2907

Max Act: 7.0407. Min Act: -0.1700

Data Index: 1557825 (Python Code)

Max Activating Token Index: 980

Text #10

Max Range: 7.2907. Min Range: -7.2907

Max Act: 6.9157. Min Act: -0.1700

Data Index: 1390014 (Python Code)

Max Activating Token Index: 981

Text #11

Max Range: 7.2907. Min Range: -7.2907

Max Act: 6.9157. Min Act: -0.1700

Data Index: 1582242 (Python Code)

Max Activating Token Index: 793

Text #12

Max Range: 7.2907. Min Range: -7.2907

Max Act: 6.8532. Min Act: -0.1700

Data Index: 1496315 (Python Code)

Max Activating Token Index: 587

Text #13

Max Range: 7.2907. Min Range: -7.2907

Max Act: 6.9157. Min Act: -0.1700

Data Index: 1451794 (Python Code)

Max Activating Token Index: 891

Text #14

Max Range: 7.2907. Min Range: -7.2907

Max Act: 6.9157. Min Act: -0.1700

Data Index: 1641359 (Python Code)

Max Activating Token Index: 494

Text #15

Max Range: 7.2907. Min Range: -7.2907

Max Act: 6.9157. Min Act: -0.1700

Data Index: 1542484 (Python Code)

Max Activating Token Index: 559

Text #16

Max Range: 7.2907. Min Range: -7.2907

Max Act: 6.8532. Min Act: -0.1700

Data Index: 1372208 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 7.2907. Min Range: -7.2907

Max Act: 6.8532. Min Act: -0.1700

Data Index: 1530799 (Python Code)

Max Activating Token Index: 963

Text #18

Max Range: 7.2907. Min Range: -7.2907

Max Act: 6.7907. Min Act: -0.1700

Data Index: 1623286 (Python Code)

Max Activating Token Index: 625

Text #19

Max Range: 7.2907. Min Range: -7.2907

Max Act: 6.7907. Min Act: -0.1700

Data Index: 1613566 (Python Code)

Max Activating Token Index: 882