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

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

Neuron 977 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.5637. Min Act: -0.1700

Data Index: 1358186 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.5637. Min Act: -0.1700

Data Index: 576911 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.5324. Min Act: -0.1700

Data Index: 1125974 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.5637. Min Act: -0.1700

Data Index: 444743 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.5011. Min Act: -0.1700

Data Index: 210063 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.5011. Min Act: -0.1700

Data Index: 1166016 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.4697. Min Act: -0.1700

Data Index: 685716 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.4697. Min Act: -0.1700

Data Index: 348255 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.4384. Min Act: -0.1700

Data Index: 1130317 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.4227. Min Act: -0.1700

Data Index: 911733 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.4227. Min Act: -0.1700

Data Index: 880755 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.4227. Min Act: -0.1700

Data Index: 1105527 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.4070. Min Act: -0.1700

Data Index: 266824 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.3913. Min Act: -0.1700

Data Index: 75209 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.4070. Min Act: -0.1700

Data Index: 904214 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.4070. Min Act: -0.1700

Data Index: 722860 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.3913. Min Act: -0.1700

Data Index: 378387 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.3913. Min Act: -0.1700

Data Index: 333613 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.3756. Min Act: -0.1700

Data Index: 210673 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.3913. Min Act: -0.1700

Data Index: 1001047 (C4 (Web Text))

Max Activating Token Index: 218