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

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

Neuron 885 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: 3.3279. Min Range: -3.3279

Max Act: 3.3279. Min Act: -0.1700

Data Index: 1090771 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.2411. Min Act: -0.1700

Data Index: 1358372 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.1931. Min Act: -0.1700

Data Index: 1156467 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.1610. Min Act: -0.1700

Data Index: 833667 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.1088. Min Act: -0.1700

Data Index: 1224401 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.1040. Min Act: -0.1700

Data Index: 1211933 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.1015. Min Act: -0.1700

Data Index: 464262 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.0927. Min Act: -0.1700

Data Index: 86280 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.0950. Min Act: -0.1700

Data Index: 465312 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.0694. Min Act: -0.1700

Data Index: 1073878 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.0771. Min Act: -0.1700

Data Index: 265067 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.0783. Min Act: -0.1700

Data Index: 137910 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.0469. Min Act: -0.1700

Data Index: 1110898 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.0565. Min Act: -0.1700

Data Index: 97787 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.0573. Min Act: -0.1700

Data Index: 133337 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.0435. Min Act: -0.1699

Data Index: 156087 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.0560. Min Act: -0.1700

Data Index: 778707 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.0368. Min Act: -0.1700

Data Index: 211792 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.0498. Min Act: -0.1699

Data Index: 1157212 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 3.3279. Min Range: -3.3279

Max Act: 3.0505. Min Act: -0.1700

Data Index: 37917 (C4 (Web Text))

Max Activating Token Index: 649