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

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

Neuron 120 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.7624. Min Act: -0.1700

Data Index: 1469280 (Python Code)

Max Activating Token Index: 920

Text #1

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.7312. Min Act: -0.1699

Data Index: 1441076 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.6062. Min Act: -0.1700

Data Index: 1429810 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.6374. Min Act: -0.1700

Data Index: 1486358 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.6374. Min Act: -0.1700

Data Index: 1588567 (Python Code)

Max Activating Token Index: 284

Text #5

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.5749. Min Act: -0.1700

Data Index: 1598167 (Python Code)

Max Activating Token Index: 665

Text #6

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.5749. Min Act: -0.1700

Data Index: 1505882 (Python Code)

Max Activating Token Index: 580

Text #7

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.6062. Min Act: -0.1700

Data Index: 1424216 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.5749. Min Act: -0.1700

Data Index: 1378620 (Python Code)

Max Activating Token Index: 562

Text #9

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.5749. Min Act: -0.1700

Data Index: 1537648 (Python Code)

Max Activating Token Index: 278

Text #10

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.6062. Min Act: -0.1700

Data Index: 1589218 (Python Code)

Max Activating Token Index: 299

Text #11

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.5749. Min Act: -0.1700

Data Index: 1460625 (Python Code)

Max Activating Token Index: 353

Text #12

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.5749. Min Act: -0.1700

Data Index: 1614837 (Python Code)

Max Activating Token Index: 966

Text #13

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.5437. Min Act: -0.1700

Data Index: 1415935 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.5749. Min Act: -0.1700

Data Index: 1385968 (Python Code)

Max Activating Token Index: 817

Text #15

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.5437. Min Act: -0.1700

Data Index: 1649473 (Python Code)

Max Activating Token Index: 946

Text #16

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.5124. Min Act: -0.1700

Data Index: 1570200 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.5749. Min Act: -0.1700

Data Index: 1559994 (Python Code)

Max Activating Token Index: 166

Text #18

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.4812. Min Act: -0.1700

Data Index: 1508917 (Python Code)

Max Activating Token Index: 463

Text #19

Max Range: 5.7624. Min Range: -5.7624

Max Act: 5.4812. Min Act: -0.1700

Data Index: 1461270 (Python Code)

Max Activating Token Index: 785