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

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

Neuron 1699 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: 3.2963. Min Range: -3.2963

Max Act: 3.2963. Min Act: -0.1700

Data Index: 1332447 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.2963. Min Act: -0.1700

Data Index: 1505749 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.2963. Min Act: -0.1700

Data Index: 1646393 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.2806. Min Act: -0.1700

Data Index: 1114249 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.2492. Min Act: -0.1700

Data Index: 1431334 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.2649. Min Act: -0.1700

Data Index: 722780 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.2492. Min Act: -0.1700

Data Index: 1550521 (Python Code)

Max Activating Token Index: 589

Text #7

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.2178. Min Act: -0.1700

Data Index: 829812 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.1863. Min Act: -0.1700

Data Index: 519621 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.1706. Min Act: -0.1700

Data Index: 1387937 (Python Code)

Max Activating Token Index: 882

Text #10

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.2178. Min Act: -0.1700

Data Index: 43664 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.1863. Min Act: -0.1700

Data Index: 1458556 (Python Code)

Max Activating Token Index: 95

Text #12

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.1548. Min Act: -0.1700

Data Index: 1492065 (Python Code)

Max Activating Token Index: 93

Text #13

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.1706. Min Act: -0.1700

Data Index: 1469733 (Python Code)

Max Activating Token Index: 95

Text #14

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.1863. Min Act: -0.1700

Data Index: 1430309 (Python Code)

Max Activating Token Index: 233

Text #15

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.2020. Min Act: -0.1700

Data Index: 984604 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.1863. Min Act: -0.1700

Data Index: 1299289 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.1548. Min Act: -0.1700

Data Index: 1616032 (Python Code)

Max Activating Token Index: 32

Text #18

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.1706. Min Act: -0.1700

Data Index: 1577425 (Python Code)

Max Activating Token Index: 548

Text #19

Max Range: 3.2963. Min Range: -3.2963

Max Act: 3.1706. Min Act: -0.1700

Data Index: 1503779 (Python Code)

Max Activating Token Index: 205