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

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

Neuron 152 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1415. Min Range: -5.1415

Max Act: 5.1415. Min Act: -0.1700

Data Index: 401105 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.9853. Min Act: -0.1700

Data Index: 1338776 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.7977. Min Act: -0.1700

Data Index: 505609 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.6415. Min Act: -0.1700

Data Index: 529696 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.5477. Min Act: -0.1700

Data Index: 887882 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.5165. Min Act: -0.1700

Data Index: 141941 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.5165. Min Act: -0.1699

Data Index: 194667 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.4540. Min Act: -0.1700

Data Index: 304396 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.4540. Min Act: -0.1700

Data Index: 313511 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.4852. Min Act: -0.1700

Data Index: 1224527 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.4540. Min Act: -0.1700

Data Index: 884572 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.4540. Min Act: -0.1700

Data Index: 332888 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.4227. Min Act: -0.1700

Data Index: 1054791 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.4227. Min Act: -0.1700

Data Index: 694978 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.3602. Min Act: -0.1700

Data Index: 587339 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.3915. Min Act: -0.1700

Data Index: 1011303 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.3602. Min Act: -0.1700

Data Index: 334146 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.3602. Min Act: -0.1700

Data Index: 593508 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.3290. Min Act: -0.1700

Data Index: 808285 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 5.1415. Min Range: -5.1415

Max Act: 4.3290. Min Act: -0.1700

Data Index: 42696 (C4 (Web Text))

Max Activating Token Index: 445