Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 173 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.4517. Min Act: -0.1700

Data Index: 1384688 (Python Code)

Max Activating Token Index: 411

Text #1

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.3924. Min Act: -0.1700

Data Index: 1598103 (Python Code)

Max Activating Token Index: 507

Text #2

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.3209. Min Act: -0.1700

Data Index: 1627118 (Python Code)

Max Activating Token Index: 109

Text #3

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.3153. Min Act: -0.1700

Data Index: 1436057 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.3183. Min Act: -0.1699

Data Index: 1646604 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.3267. Min Act: -0.1700

Data Index: 1549800 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.2866. Min Act: -0.1700

Data Index: 1612321 (Python Code)

Max Activating Token Index: 864

Text #7

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.2417. Min Act: -0.1700

Data Index: 1438363 (Python Code)

Max Activating Token Index: 776

Text #8

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.2640. Min Act: -0.1700

Data Index: 1612758 (Python Code)

Max Activating Token Index: 300

Text #9

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.2240. Min Act: -0.1700

Data Index: 1536396 (Python Code)

Max Activating Token Index: 791

Text #10

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.2137. Min Act: -0.1700

Data Index: 1531198 (Python Code)

Max Activating Token Index: 407

Text #11

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.2042. Min Act: -0.1700

Data Index: 1564261 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.2005. Min Act: -0.1700

Data Index: 1443813 (Python Code)

Max Activating Token Index: 420

Text #13

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.2044. Min Act: -0.1700

Data Index: 1409044 (Python Code)

Max Activating Token Index: 398

Text #14

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.2034. Min Act: -0.1699

Data Index: 1656621 (Python Code)

Max Activating Token Index: 28

Text #15

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.1988. Min Act: -0.1700

Data Index: 1375274 (Python Code)

Max Activating Token Index: 992

Text #16

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.2003. Min Act: -0.1700

Data Index: 1443452 (Python Code)

Max Activating Token Index: 168

Text #17

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.1771. Min Act: -0.1700

Data Index: 1489479 (Python Code)

Max Activating Token Index: 761

Text #18

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.1774. Min Act: -0.1700

Data Index: 1389626 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 3.4517. Min Range: -3.4517

Max Act: 3.1777. Min Act: -0.1700

Data Index: 1589107 (Python Code)

Max Activating Token Index: 87