Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1463 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.9000. Min Act: -0.1700

Data Index: 1123464 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.9312. Min Act: -0.1700

Data Index: 821177 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.9312. Min Act: -0.1700

Data Index: 573444 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.5875. Min Act: -0.1700

Data Index: 280856 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.5875. Min Act: -0.1700

Data Index: 737869 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.5875. Min Act: -0.1700

Data Index: 680727 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.5250. Min Act: -0.1700

Data Index: 323711 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.5250. Min Act: -0.1700

Data Index: 125903 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.5250. Min Act: -0.1700

Data Index: 1055344 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.4937. Min Act: -0.1700

Data Index: 740115 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.4625. Min Act: -0.1700

Data Index: 158551 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.4312. Min Act: -0.1700

Data Index: 383782 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.4312. Min Act: -0.1700

Data Index: 485253 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.4937. Min Act: -0.1700

Data Index: 765014 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.4312. Min Act: -0.1700

Data Index: 61577 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.4000. Min Act: -0.1700

Data Index: 1268230 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.3687. Min Act: -0.1700

Data Index: 1340198 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.3687. Min Act: -0.1700

Data Index: 125937 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.2750. Min Act: -0.1700

Data Index: 750513 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 5.9312. Min Range: -5.9312

Max Act: 5.3062. Min Act: -0.1700

Data Index: 121361 (C4 (Web Text))

Max Activating Token Index: 751