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

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

Neuron 1241 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: 3.9879. Min Range: -3.9879

Max Act: 3.9879. Min Act: -0.1699

Data Index: 1649884 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.8424. Min Act: -0.1686

Data Index: 1630365 (Python Code)

Max Activating Token Index: 253

Text #2

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7979. Min Act: -0.1686

Data Index: 316893 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7906. Min Act: -0.1691

Data Index: 1451759 (Python Code)

Max Activating Token Index: 766

Text #4

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7965. Min Act: -0.1686

Data Index: 1495885 (Python Code)

Max Activating Token Index: 373

Text #5

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7812. Min Act: -0.1686

Data Index: 1537671 (Python Code)

Max Activating Token Index: 932

Text #6

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7566. Min Act: -0.1686

Data Index: 1394671 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7593. Min Act: -0.1692

Data Index: 1562187 (Python Code)

Max Activating Token Index: 973

Text #8

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7679. Min Act: -0.1686

Data Index: 1486800 (Python Code)

Max Activating Token Index: 861

Text #9

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7533. Min Act: -0.1699

Data Index: 1652085 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7554. Min Act: -0.1686

Data Index: 1366094 (Python Code)

Max Activating Token Index: 311

Text #11

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7412. Min Act: -0.1699

Data Index: 1441276 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7185. Min Act: -0.1686

Data Index: 1597840 (Python Code)

Max Activating Token Index: 158

Text #13

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7307. Min Act: -0.1686

Data Index: 1624408 (Python Code)

Max Activating Token Index: 50

Text #14

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7192. Min Act: -0.1698

Data Index: 1399614 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6791. Min Act: -0.1686

Data Index: 1469810 (Python Code)

Max Activating Token Index: 76

Text #16

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6982. Min Act: -0.1699

Data Index: 1478965 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7042. Min Act: -0.1686

Data Index: 1368018 (Python Code)

Max Activating Token Index: 96

Text #18

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6642. Min Act: -0.1686

Data Index: 1394010 (Python Code)

Max Activating Token Index: 991

Text #19

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6548. Min Act: -0.1699

Data Index: 1445511 (Python Code)

Max Activating Token Index: 14