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

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

Neuron 739 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: 3.4120. Min Range: -3.4120

Max Act: 3.4120. Min Act: -0.1700

Data Index: 760839 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.4120. Min Act: -0.1700

Data Index: 1240294 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.3650. Min Act: -0.1700

Data Index: 459796 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.3650. Min Act: -0.1700

Data Index: 1002027 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.3493. Min Act: -0.1700

Data Index: 304196 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.3022. Min Act: -0.1700

Data Index: 1220816 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.3493. Min Act: -0.1700

Data Index: 1286539 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.2865. Min Act: -0.1700

Data Index: 906134 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.3022. Min Act: -0.1700

Data Index: 1336825 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.3179. Min Act: -0.1700

Data Index: 140468 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.3336. Min Act: -0.1700

Data Index: 1068061 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.3022. Min Act: -0.1700

Data Index: 113995 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.3022. Min Act: -0.1700

Data Index: 282311 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.3807. Min Act: -0.1700

Data Index: 877415 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.2865. Min Act: -0.1700

Data Index: 1107828 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.2865. Min Act: -0.1700

Data Index: 824667 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.2550. Min Act: -0.1700

Data Index: 794068 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.3022. Min Act: -0.1700

Data Index: 57979 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.1921. Min Act: -0.1700

Data Index: 1277398 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 3.4120. Min Range: -3.4120

Max Act: 3.2865. Min Act: -0.1700

Data Index: 1230533 (C4 (Web Text))

Max Activating Token Index: 359