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

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

Neuron 1714 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: 3.4435. Min Range: -3.4435

Max Act: 3.4435. Min Act: -0.1700

Data Index: 1026531 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.3202. Min Act: -0.1700

Data Index: 574117 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.2607. Min Act: -0.1700

Data Index: 979253 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.2090. Min Act: -0.1700

Data Index: 992213 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.2372. Min Act: -0.1700

Data Index: 1034809 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.2286. Min Act: -0.1700

Data Index: 439842 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.1940. Min Act: -0.1700

Data Index: 750836 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.2028. Min Act: -0.1700

Data Index: 1136161 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.1967. Min Act: -0.1700

Data Index: 1131364 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.1702. Min Act: -0.1700

Data Index: 279566 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.1875. Min Act: -0.1700

Data Index: 31106 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.1867. Min Act: -0.1700

Data Index: 306470 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.1657. Min Act: -0.1700

Data Index: 248897 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.1908. Min Act: -0.1700

Data Index: 1322339 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.1591. Min Act: -0.1700

Data Index: 611541 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.1585. Min Act: -0.1700

Data Index: 316509 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.1536. Min Act: -0.1700

Data Index: 112545 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.1268. Min Act: -0.1700

Data Index: 1278426 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.1300. Min Act: -0.1700

Data Index: 543958 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 3.4435. Min Range: -3.4435

Max Act: 3.1290. Min Act: -0.1700

Data Index: 421661 (C4 (Web Text))

Max Activating Token Index: 226