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

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

Neuron 1158 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: 5.7555. Min Range: -5.7555

Max Act: 5.7555. Min Act: -0.1700

Data Index: 1114803 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.7555. Min Act: -0.1700

Data Index: 720453 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.6930. Min Act: -0.1700

Data Index: 33056 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.5992. Min Act: -0.1700

Data Index: 1191005 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.5992. Min Act: -0.1700

Data Index: 1240624 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.5055. Min Act: -0.1700

Data Index: 793511 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.4430. Min Act: -0.1700

Data Index: 868794 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.4430. Min Act: -0.1700

Data Index: 14425 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.3492. Min Act: -0.1700

Data Index: 1213095 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.3805. Min Act: -0.1700

Data Index: 1224913 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.3492. Min Act: -0.1700

Data Index: 1036267 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.3492. Min Act: -0.1700

Data Index: 168432 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2867. Min Act: -0.1700

Data Index: 316400 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2555. Min Act: -0.1700

Data Index: 691990 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2867. Min Act: -0.1700

Data Index: 378200 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2555. Min Act: -0.1700

Data Index: 1007896 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.3180. Min Act: -0.1700

Data Index: 726647 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2555. Min Act: -0.1700

Data Index: 603796 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2242. Min Act: -0.1700

Data Index: 40025 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 5.7555. Min Range: -5.7555

Max Act: 5.2242. Min Act: -0.1700

Data Index: 72410 (C4 (Web Text))

Max Activating Token Index: 518