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

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

Neuron 1787 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: 4.9121. Min Range: -4.9121

Max Act: 4.9121. Min Act: -0.1700

Data Index: 1313266 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.7780. Min Act: -0.1700

Data Index: 1598361 (Python Code)

Max Activating Token Index: 794

Text #2

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.7474. Min Act: -0.1700

Data Index: 1531604 (Python Code)

Max Activating Token Index: 147

Text #3

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.5911. Min Act: -0.1700

Data Index: 543208 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.5858. Min Act: -0.1697

Data Index: 1337233 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.5541. Min Act: -0.1699

Data Index: 1217963 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.4753. Min Act: -0.1700

Data Index: 161113 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.4441. Min Act: -0.1700

Data Index: 1340438 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.4562. Min Act: -0.1698

Data Index: 1438697 (Python Code)

Max Activating Token Index: 731

Text #9

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.4228. Min Act: -0.1700

Data Index: 1438588 (Python Code)

Max Activating Token Index: 576

Text #10

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.3608. Min Act: -0.1700

Data Index: 1459730 (Python Code)

Max Activating Token Index: 125

Text #11

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.3358. Min Act: -0.1700

Data Index: 620626 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.3120. Min Act: -0.1699

Data Index: 1509257 (Python Code)

Max Activating Token Index: 1009

Text #13

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.3352. Min Act: -0.1700

Data Index: 162823 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.2692. Min Act: -0.1700

Data Index: 1360909 (Python Code)

Max Activating Token Index: 512

Text #15

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.2707. Min Act: -0.1700

Data Index: 1628581 (Python Code)

Max Activating Token Index: 825

Text #16

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.2985. Min Act: -0.1700

Data Index: 599265 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.2714. Min Act: -0.1699

Data Index: 534652 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.2505. Min Act: -0.1700

Data Index: 826014 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.2402. Min Act: -0.1699

Data Index: 1463800 (Python Code)

Max Activating Token Index: 191