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

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

Neuron 1341 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.4791. Min Act: -0.1700

Data Index: 1173925 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.4164. Min Act: -0.1700

Data Index: 1049726 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3537. Min Act: -0.1700

Data Index: 657004 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3223. Min Act: -0.1700

Data Index: 124286 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.2909. Min Act: -0.1700

Data Index: 254633 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3223. Min Act: -0.1700

Data Index: 99214 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3223. Min Act: -0.1700

Data Index: 965631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3223. Min Act: -0.1700

Data Index: 887532 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3223. Min Act: -0.1700

Data Index: 1319619 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3223. Min Act: -0.1700

Data Index: 448928 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.2909. Min Act: -0.1700

Data Index: 214948 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3537. Min Act: -0.1700

Data Index: 281617 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.2594. Min Act: -0.1700

Data Index: 536238 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.2909. Min Act: -0.1700

Data Index: 85205 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.2909. Min Act: -0.1700

Data Index: 988819 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.1965. Min Act: -0.1700

Data Index: 1651601 (Python Code)

Max Activating Token Index: 624

Text #16

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.2909. Min Act: -0.1700

Data Index: 1031155 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.2594. Min Act: -0.1700

Data Index: 584052 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.2594. Min Act: -0.1700

Data Index: 944050 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.2594. Min Act: -0.1700

Data Index: 453291 (C4 (Web Text))

Max Activating Token Index: 1023