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

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

Neuron 560 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: 3.7752. Min Range: -3.7752

Max Act: 3.7752. Min Act: -0.1700

Data Index: 1594135 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.3456. Min Act: -0.1700

Data Index: 848597 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.3134. Min Act: -0.1700

Data Index: 518629 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.2638. Min Act: -0.1700

Data Index: 875497 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.2590. Min Act: -0.1700

Data Index: 175513 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.2610. Min Act: -0.1700

Data Index: 101583 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.2521. Min Act: -0.1700

Data Index: 1551294 (Python Code)

Max Activating Token Index: 160

Text #7

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.2563. Min Act: -0.1700

Data Index: 15819 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.2326. Min Act: -0.1700

Data Index: 986466 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.2038. Min Act: -0.1700

Data Index: 607922 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.1758. Min Act: -0.1700

Data Index: 113880 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.1835. Min Act: -0.1699

Data Index: 528551 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.1519. Min Act: -0.1700

Data Index: 640639 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.1647. Min Act: -0.1700

Data Index: 1185777 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.1601. Min Act: -0.1700

Data Index: 41470 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.1530. Min Act: -0.1700

Data Index: 802112 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.1344. Min Act: -0.1700

Data Index: 599290 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.1305. Min Act: -0.1700

Data Index: 786105 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.1402. Min Act: -0.1700

Data Index: 1342328 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 3.7752. Min Range: -3.7752

Max Act: 3.1474. Min Act: -0.1700

Data Index: 731744 (C4 (Web Text))

Max Activating Token Index: 577