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

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

Neuron 976 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: 3.8330. Min Range: -3.8330

Max Act: 3.8330. Min Act: -0.1700

Data Index: 578436 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.7704. Min Act: -0.1700

Data Index: 1216945 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.7391. Min Act: -0.1700

Data Index: 940721 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.7391. Min Act: -0.1700

Data Index: 958616 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6765. Min Act: -0.1700

Data Index: 773477 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.7391. Min Act: -0.1700

Data Index: 627307 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6765. Min Act: -0.1700

Data Index: 260466 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6765. Min Act: -0.1700

Data Index: 1034141 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6452. Min Act: -0.1700

Data Index: 1096211 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.7078. Min Act: -0.1700

Data Index: 728819 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6765. Min Act: -0.1700

Data Index: 142013 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6765. Min Act: -0.1700

Data Index: 118791 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6765. Min Act: -0.1700

Data Index: 140554 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6765. Min Act: -0.1700

Data Index: 489059 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6452. Min Act: -0.1700

Data Index: 195542 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6765. Min Act: -0.1700

Data Index: 253007 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6139. Min Act: -0.1700

Data Index: 1046750 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6452. Min Act: -0.1700

Data Index: 287035 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6452. Min Act: -0.1700

Data Index: 682427 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 3.8330. Min Range: -3.8330

Max Act: 3.6452. Min Act: -0.1700

Data Index: 882081 (C4 (Web Text))

Max Activating Token Index: 703