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

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

Neuron 849 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: 3.8558. Min Range: -3.8558

Max Act: 3.8558. Min Act: -0.1700

Data Index: 1594920 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.8355. Min Act: -0.1700

Data Index: 1583821 (Python Code)

Max Activating Token Index: 116

Text #2

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.7979. Min Act: -0.1700

Data Index: 1532257 (Python Code)

Max Activating Token Index: 829

Text #3

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.7494. Min Act: -0.1700

Data Index: 1652531 (Python Code)

Max Activating Token Index: 990

Text #4

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.7675. Min Act: -0.1700

Data Index: 1419737 (Python Code)

Max Activating Token Index: 124

Text #5

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.7536. Min Act: -0.1700

Data Index: 1538939 (Python Code)

Max Activating Token Index: 834

Text #6

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.7599. Min Act: -0.1700

Data Index: 1651233 (Python Code)

Max Activating Token Index: 49

Text #7

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.7326. Min Act: -0.1700

Data Index: 1450306 (Python Code)

Max Activating Token Index: 178

Text #8

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.7448. Min Act: -0.1700

Data Index: 1637843 (Python Code)

Max Activating Token Index: 18

Text #9

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.7568. Min Act: -0.1700

Data Index: 1525074 (Python Code)

Max Activating Token Index: 731

Text #10

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.7405. Min Act: -0.1700

Data Index: 1606844 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.7420. Min Act: -0.1700

Data Index: 1415499 (Python Code)

Max Activating Token Index: 462

Text #12

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.7242. Min Act: -0.1700

Data Index: 1424770 (Python Code)

Max Activating Token Index: 498

Text #13

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.7202. Min Act: -0.1700

Data Index: 1631427 (Python Code)

Max Activating Token Index: 35

Text #14

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.6901. Min Act: -0.1700

Data Index: 1405551 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.6733. Min Act: -0.1700

Data Index: 1484958 (Python Code)

Max Activating Token Index: 211

Text #16

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.6805. Min Act: -0.1700

Data Index: 1561064 (Python Code)

Max Activating Token Index: 761

Text #17

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.6550. Min Act: -0.1700

Data Index: 1653892 (Python Code)

Max Activating Token Index: 413

Text #18

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.6444. Min Act: -0.1700

Data Index: 1468728 (Python Code)

Max Activating Token Index: 510

Text #19

Max Range: 3.8558. Min Range: -3.8558

Max Act: 3.6597. Min Act: -0.1700

Data Index: 1448039 (Python Code)

Max Activating Token Index: 434