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

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

Neuron 1062 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: 3.7363. Min Range: -3.7363

Max Act: 3.7363. Min Act: -0.1700

Data Index: 827204 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.6784. Min Act: -0.1700

Data Index: 783162 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.6378. Min Act: -0.1700

Data Index: 9846 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.6292. Min Act: -0.1700

Data Index: 1049118 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.5787. Min Act: -0.1700

Data Index: 436120 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.5538. Min Act: -0.1700

Data Index: 553086 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.5278. Min Act: -0.1700

Data Index: 1303575 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.5045. Min Act: -0.1700

Data Index: 516644 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.5042. Min Act: -0.1700

Data Index: 195357 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.4757. Min Act: -0.1700

Data Index: 363958 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.4428. Min Act: -0.1700

Data Index: 1335259 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.4755. Min Act: -0.1700

Data Index: 600395 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.4711. Min Act: -0.1700

Data Index: 1350384 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.4852. Min Act: -0.1700

Data Index: 1074065 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.4831. Min Act: -0.1700

Data Index: 1345668 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.4504. Min Act: -0.1700

Data Index: 534141 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.3898. Min Act: -0.1700

Data Index: 810934 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.3991. Min Act: -0.1700

Data Index: 1004904 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.4341. Min Act: -0.1700

Data Index: 360023 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 3.7363. Min Range: -3.7363

Max Act: 3.4075. Min Act: -0.1700

Data Index: 649771 (C4 (Web Text))

Max Activating Token Index: 971