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

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

Neuron 925 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0969. Min Range: -5.0969

Max Act: 5.0969. Min Act: -0.1700

Data Index: 1456671 (Python Code)

Max Activating Token Index: 97

Text #1

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.9562. Min Act: -0.1700

Data Index: 1493428 (Python Code)

Max Activating Token Index: 246

Text #2

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.8156. Min Act: -0.1700

Data Index: 1462750 (Python Code)

Max Activating Token Index: 155

Text #3

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.8312. Min Act: -0.1699

Data Index: 1415146 (Python Code)

Max Activating Token Index: 155

Text #4

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.8156. Min Act: -0.1700

Data Index: 1503849 (Python Code)

Max Activating Token Index: 906

Text #5

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.8000. Min Act: -0.1700

Data Index: 1409293 (Python Code)

Max Activating Token Index: 205

Text #6

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.7687. Min Act: -0.1700

Data Index: 1519293 (Python Code)

Max Activating Token Index: 766

Text #7

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.8000. Min Act: -0.1699

Data Index: 164922 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.7531. Min Act: -0.1700

Data Index: 195246 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.7218. Min Act: -0.1700

Data Index: 1609402 (Python Code)

Max Activating Token Index: 281

Text #10

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.7218. Min Act: -0.1700

Data Index: 1545783 (Python Code)

Max Activating Token Index: 809

Text #11

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.7375. Min Act: -0.1700

Data Index: 1454102 (Python Code)

Max Activating Token Index: 108

Text #12

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.7062. Min Act: -0.1700

Data Index: 1468697 (Python Code)

Max Activating Token Index: 186

Text #13

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.6906. Min Act: -0.1699

Data Index: 1555357 (Python Code)

Max Activating Token Index: 914

Text #14

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.6281. Min Act: -0.1699

Data Index: 1403796 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.6593. Min Act: -0.1700

Data Index: 453421 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.6593. Min Act: -0.1700

Data Index: 1604810 (Python Code)

Max Activating Token Index: 485

Text #17

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.6281. Min Act: -0.1700

Data Index: 1473693 (Python Code)

Max Activating Token Index: 802

Text #18

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.6906. Min Act: -0.1700

Data Index: 1462862 (Python Code)

Max Activating Token Index: 611

Text #19

Max Range: 5.0969. Min Range: -5.0969

Max Act: 4.6750. Min Act: -0.1700

Data Index: 1436923 (Python Code)

Max Activating Token Index: 224