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

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

Neuron 465 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: 3.4207. Min Range: -3.4207

Max Act: 3.4050. Min Act: -0.1700

Data Index: 1540700 (Python Code)

Max Activating Token Index: 574

Text #1

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.4207. Min Act: -0.1700

Data Index: 1587462 (Python Code)

Max Activating Token Index: 196

Text #2

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.3266. Min Act: -0.1700

Data Index: 1404973 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2638. Min Act: -0.1700

Data Index: 1654712 (Python Code)

Max Activating Token Index: 933

Text #4

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2638. Min Act: -0.1700

Data Index: 1548388 (Python Code)

Max Activating Token Index: 689

Text #5

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2638. Min Act: -0.1700

Data Index: 1406974 (Python Code)

Max Activating Token Index: 781

Text #6

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2480. Min Act: -0.1700

Data Index: 1478203 (Python Code)

Max Activating Token Index: 909

Text #7

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2323. Min Act: -0.1700

Data Index: 1413610 (Python Code)

Max Activating Token Index: 434

Text #8

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2323. Min Act: -0.1700

Data Index: 1370535 (Python Code)

Max Activating Token Index: 734

Text #9

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2323. Min Act: -0.1700

Data Index: 1639489 (Python Code)

Max Activating Token Index: 349

Text #10

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2323. Min Act: -0.1700

Data Index: 1611212 (Python Code)

Max Activating Token Index: 241

Text #11

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2480. Min Act: -0.1700

Data Index: 1416661 (Python Code)

Max Activating Token Index: 935

Text #12

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2323. Min Act: -0.1700

Data Index: 1375980 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2166. Min Act: -0.1700

Data Index: 1621377 (Python Code)

Max Activating Token Index: 257

Text #14

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2009. Min Act: -0.1700

Data Index: 1501210 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2009. Min Act: -0.1700

Data Index: 1655305 (Python Code)

Max Activating Token Index: 286

Text #16

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2166. Min Act: -0.1700

Data Index: 1638824 (Python Code)

Max Activating Token Index: 915

Text #17

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2009. Min Act: -0.1700

Data Index: 1418334 (Python Code)

Max Activating Token Index: 558

Text #18

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.2009. Min Act: -0.1700

Data Index: 1578877 (Python Code)

Max Activating Token Index: 174

Text #19

Max Range: 3.4207. Min Range: -3.4207

Max Act: 3.1694. Min Act: -0.1700

Data Index: 1450725 (Python Code)

Max Activating Token Index: 288