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

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

Neuron 1313 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: 5.3244. Min Range: -5.3244

Max Act: 5.3244. Min Act: -0.1700

Data Index: 1489185 (Python Code)

Max Activating Token Index: 212

Text #1

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.2306. Min Act: -0.1699

Data Index: 1440310 (Python Code)

Max Activating Token Index: 257

Text #2

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.2931. Min Act: -0.1700

Data Index: 1569326 (Python Code)

Max Activating Token Index: 200

Text #3

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.1994. Min Act: -0.1700

Data Index: 1618645 (Python Code)

Max Activating Token Index: 190

Text #4

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.1994. Min Act: -0.1699

Data Index: 1572253 (Python Code)

Max Activating Token Index: 176

Text #5

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.1056. Min Act: -0.1700

Data Index: 1515227 (Python Code)

Max Activating Token Index: 677

Text #6

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.0744. Min Act: -0.1700

Data Index: 1640980 (Python Code)

Max Activating Token Index: 250

Text #7

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.0744. Min Act: -0.1700

Data Index: 1550587 (Python Code)

Max Activating Token Index: 315

Text #8

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.0119. Min Act: -0.1700

Data Index: 1365569 (Python Code)

Max Activating Token Index: 164

Text #9

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.0431. Min Act: -0.1699

Data Index: 1366938 (Python Code)

Max Activating Token Index: 725

Text #10

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.0431. Min Act: -0.1700

Data Index: 163522 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.0431. Min Act: -0.1700

Data Index: 1475412 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.0431. Min Act: -0.1700

Data Index: 1476341 (Python Code)

Max Activating Token Index: 721

Text #13

Max Range: 5.3244. Min Range: -5.3244

Max Act: 4.9806. Min Act: -0.1700

Data Index: 414257 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.0119. Min Act: -0.1699

Data Index: 1375317 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.0431. Min Act: -0.1697

Data Index: 1371044 (Python Code)

Max Activating Token Index: 101

Text #16

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.0431. Min Act: -0.1700

Data Index: 1608774 (Python Code)

Max Activating Token Index: 237

Text #17

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.0119. Min Act: -0.1700

Data Index: 10646 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.0431. Min Act: -0.1700

Data Index: 1547568 (Python Code)

Max Activating Token Index: 944

Text #19

Max Range: 5.3244. Min Range: -5.3244

Max Act: 5.0119. Min Act: -0.1700

Data Index: 1635814 (Python Code)

Max Activating Token Index: 303