Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1848 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.3293. Min Act: -0.1700

Data Index: 74267 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.2355. Min Act: -0.1700

Data Index: 93974 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.2668. Min Act: -0.1700

Data Index: 998972 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.2355. Min Act: -0.1700

Data Index: 41773 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1105. Min Act: -0.1700

Data Index: 4713 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.2355. Min Act: -0.1700

Data Index: 513626 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.2043. Min Act: -0.1700

Data Index: 1119603 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1418. Min Act: -0.1700

Data Index: 796529 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1105. Min Act: -0.1700

Data Index: 440248 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1730. Min Act: -0.1700

Data Index: 656319 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.0793. Min Act: -0.1700

Data Index: 151583 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1105. Min Act: -0.1700

Data Index: 61037 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1418. Min Act: -0.1700

Data Index: 1088404 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1105. Min Act: -0.1700

Data Index: 632477 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1105. Min Act: -0.1700

Data Index: 1337850 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.0480. Min Act: -0.1700

Data Index: 894775 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1105. Min Act: -0.1700

Data Index: 959603 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.0793. Min Act: -0.1700

Data Index: 136874 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1105. Min Act: -0.1700

Data Index: 653865 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1105. Min Act: -0.1700

Data Index: 99829 (C4 (Web Text))

Max Activating Token Index: 814