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

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

Neuron 1265 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: 3.3208. Min Range: -3.3208

Max Act: 3.3208. Min Act: -0.1700

Data Index: 752690 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2990. Min Act: -0.1700

Data Index: 1291543 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2753. Min Act: -0.1700

Data Index: 65926 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2564. Min Act: -0.1700

Data Index: 109778 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2531. Min Act: -0.1700

Data Index: 601384 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2406. Min Act: -0.1700

Data Index: 545050 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2134. Min Act: -0.1700

Data Index: 929099 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2144. Min Act: -0.1700

Data Index: 997222 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2140. Min Act: -0.1700

Data Index: 309839 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.1576. Min Act: -0.1700

Data Index: 719010 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.1797. Min Act: -0.1700

Data Index: 407290 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.1798. Min Act: -0.1700

Data Index: 135801 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.1586. Min Act: -0.1700

Data Index: 1168536 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.1399. Min Act: -0.1700

Data Index: 1207982 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.1515. Min Act: -0.1700

Data Index: 775890 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.1536. Min Act: -0.1700

Data Index: 74716 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.1490. Min Act: -0.1700

Data Index: 892816 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.1508. Min Act: -0.1700

Data Index: 145271 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.1332. Min Act: -0.1700

Data Index: 1111354 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.1346. Min Act: -0.1700

Data Index: 1309714 (C4 (Web Text))

Max Activating Token Index: 27