Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1937 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.0471. Min Range: -3.0471

Max Act: 3.0471. Min Act: -0.1697

Data Index: 1639261 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9839. Min Act: -0.1700

Data Index: 1369592 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9997. Min Act: -0.1700

Data Index: 1383211 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9680. Min Act: -0.1700

Data Index: 1495617 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9997. Min Act: -0.1700

Data Index: 1596987 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9680. Min Act: -0.1700

Data Index: 496258 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9522. Min Act: -0.1700

Data Index: 1629118 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9680. Min Act: -0.1700

Data Index: 1544201 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9522. Min Act: -0.1700

Data Index: 1429476 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9522. Min Act: -0.1700

Data Index: 1507729 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9522. Min Act: -0.1700

Data Index: 1475674 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9522. Min Act: -0.1699

Data Index: 1648296 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9364. Min Act: -0.1700

Data Index: 1504174 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9205. Min Act: -0.1700

Data Index: 1648887 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9364. Min Act: -0.1700

Data Index: 1466833 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9205. Min Act: -0.1699

Data Index: 1582688 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9364. Min Act: -0.1700

Data Index: 1457658 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9205. Min Act: -0.1700

Data Index: 1601803 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9205. Min Act: -0.1700

Data Index: 1629388 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 3.0471. Min Range: -3.0471

Max Act: 2.9205. Min Act: -0.1700

Data Index: 1411290 (Python Code)

Max Activating Token Index: 1023