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

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

Neuron 1803 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: 3.2094. Min Range: -3.2094

Max Act: 3.2094. Min Act: -0.1700

Data Index: 244476 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1853. Min Act: -0.1700

Data Index: 1045467 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1675. Min Act: -0.1700

Data Index: 850518 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1733. Min Act: -0.1700

Data Index: 1333402 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1505. Min Act: -0.1700

Data Index: 177071 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1170. Min Act: -0.1700

Data Index: 1289425 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0969. Min Act: -0.1700

Data Index: 797026 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1174. Min Act: -0.1700

Data Index: 707592 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0758. Min Act: -0.1700

Data Index: 387481 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0726. Min Act: -0.1699

Data Index: 575221 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0578. Min Act: -0.1699

Data Index: 28266 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0603. Min Act: -0.1700

Data Index: 719932 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0716. Min Act: -0.1700

Data Index: 208934 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0524. Min Act: -0.1700

Data Index: 461669 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0322. Min Act: -0.1700

Data Index: 366155 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0518. Min Act: -0.1700

Data Index: 877893 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0512. Min Act: -0.1699

Data Index: 296770 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0409. Min Act: -0.1700

Data Index: 1073591 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0460. Min Act: -0.1700

Data Index: 1147360 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0511. Min Act: -0.1700

Data Index: 747564 (C4 (Web Text))

Max Activating Token Index: 394