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

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

Neuron 2025 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: 3.6064. Min Range: -3.6064

Max Act: 3.6064. Min Act: -0.1700

Data Index: 1442924 (Python Code)

Max Activating Token Index: 479

Text #1

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.5595. Min Act: -0.1700

Data Index: 1378755 (Python Code)

Max Activating Token Index: 79

Text #2

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.5281. Min Act: -0.1700

Data Index: 1407357 (Python Code)

Max Activating Token Index: 405

Text #3

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.5281. Min Act: -0.1700

Data Index: 1558707 (Python Code)

Max Activating Token Index: 291

Text #4

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.4968. Min Act: -0.1700

Data Index: 1441850 (Python Code)

Max Activating Token Index: 243

Text #5

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.4184. Min Act: -0.1700

Data Index: 1574389 (Python Code)

Max Activating Token Index: 486

Text #6

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.4184. Min Act: -0.1700

Data Index: 1425801 (Python Code)

Max Activating Token Index: 943

Text #7

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.3870. Min Act: -0.1700

Data Index: 1494552 (Python Code)

Max Activating Token Index: 487

Text #8

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.3400. Min Act: -0.1700

Data Index: 1450019 (Python Code)

Max Activating Token Index: 226

Text #9

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.3557. Min Act: -0.1700

Data Index: 1446505 (Python Code)

Max Activating Token Index: 1019

Text #10

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.3400. Min Act: -0.1700

Data Index: 1475372 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.3557. Min Act: -0.1700

Data Index: 1469198 (Python Code)

Max Activating Token Index: 689

Text #12

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.3400. Min Act: -0.1700

Data Index: 1512462 (Python Code)

Max Activating Token Index: 880

Text #13

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.3400. Min Act: -0.1700

Data Index: 1619063 (Python Code)

Max Activating Token Index: 819

Text #14

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.3400. Min Act: -0.1700

Data Index: 1446362 (Python Code)

Max Activating Token Index: 971

Text #15

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.3243. Min Act: -0.1700

Data Index: 1595078 (Python Code)

Max Activating Token Index: 490

Text #16

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.3243. Min Act: -0.1700

Data Index: 1375048 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.3400. Min Act: -0.1700

Data Index: 1476429 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.3400. Min Act: -0.1700

Data Index: 1463328 (Python Code)

Max Activating Token Index: 704

Text #19

Max Range: 3.6064. Min Range: -3.6064

Max Act: 3.3400. Min Act: -0.1700

Data Index: 1543159 (Python Code)

Max Activating Token Index: 49