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

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

Neuron 2046 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: 3.3752. Min Range: -3.3752

Max Act: 3.3752. Min Act: -0.1700

Data Index: 1161589 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2818. Min Act: -0.1700

Data Index: 510437 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2735. Min Act: -0.1700

Data Index: 839008 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2524. Min Act: -0.1700

Data Index: 263083 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2223. Min Act: -0.1700

Data Index: 282751 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2171. Min Act: -0.1700

Data Index: 1104775 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1736. Min Act: -0.1700

Data Index: 1267618 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1692. Min Act: -0.1700

Data Index: 1004042 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1655. Min Act: -0.1700

Data Index: 54942 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1484. Min Act: -0.1700

Data Index: 66351 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1677. Min Act: -0.1700

Data Index: 281017 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1426. Min Act: -0.1700

Data Index: 652810 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1488. Min Act: -0.1700

Data Index: 557394 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1608. Min Act: -0.1700

Data Index: 1059973 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1308. Min Act: -0.1700

Data Index: 151803 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1363. Min Act: -0.1700

Data Index: 1312529 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1373. Min Act: -0.1700

Data Index: 632533 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1375. Min Act: -0.1700

Data Index: 18587 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1438. Min Act: -0.1700

Data Index: 622155 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.1192. Min Act: -0.1700

Data Index: 1025586 (C4 (Web Text))

Max Activating Token Index: 33