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

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

Neuron 946 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: 2.9822. Min Range: -2.9822

Max Act: 2.9822. Min Act: -0.1700

Data Index: 1454846 (Python Code)

Max Activating Token Index: 118

Text #1

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.9391. Min Act: -0.1700

Data Index: 516577 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.9529. Min Act: -0.1700

Data Index: 1620198 (Python Code)

Max Activating Token Index: 891

Text #3

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.9098. Min Act: -0.1700

Data Index: 523483 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.9011. Min Act: -0.1699

Data Index: 1385396 (Python Code)

Max Activating Token Index: 559

Text #5

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.9054. Min Act: -0.1700

Data Index: 88125 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8847. Min Act: -0.1698

Data Index: 779246 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8828. Min Act: -0.1700

Data Index: 1372568 (Python Code)

Max Activating Token Index: 866

Text #8

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8911. Min Act: -0.1700

Data Index: 1645529 (Python Code)

Max Activating Token Index: 982

Text #9

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8838. Min Act: -0.1699

Data Index: 938512 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8932. Min Act: -0.1700

Data Index: 249756 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8718. Min Act: -0.1700

Data Index: 427224 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8748. Min Act: -0.1700

Data Index: 779146 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8771. Min Act: -0.1699

Data Index: 276001 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8576. Min Act: -0.1699

Data Index: 1411376 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8604. Min Act: -0.1700

Data Index: 1404690 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8459. Min Act: -0.1700

Data Index: 1421068 (Python Code)

Max Activating Token Index: 683

Text #17

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8484. Min Act: -0.1700

Data Index: 732303 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8262. Min Act: -0.1700

Data Index: 1177249 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 2.9822. Min Range: -2.9822

Max Act: 2.8415. Min Act: -0.1700

Data Index: 1489236 (Python Code)

Max Activating Token Index: 589