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

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

Neuron 1040 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: 3.7033. Min Range: -3.7033

Max Act: 3.7033. Min Act: -0.1700

Data Index: 416462 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.7033. Min Act: -0.1700

Data Index: 670708 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.6094. Min Act: -0.1700

Data Index: 289050 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.5468. Min Act: -0.1700

Data Index: 383644 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.6564. Min Act: -0.1700

Data Index: 1217181 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.5311. Min Act: -0.1700

Data Index: 1328045 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.5781. Min Act: -0.1700

Data Index: 567649 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.5468. Min Act: -0.1700

Data Index: 803895 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.5155. Min Act: -0.1700

Data Index: 18788 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.4057. Min Act: -0.1700

Data Index: 1044950 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.4998. Min Act: -0.1700

Data Index: 554264 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.5155. Min Act: -0.1700

Data Index: 711409 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.4528. Min Act: -0.1700

Data Index: 849365 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.3744. Min Act: -0.1700

Data Index: 1293343 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.3587. Min Act: -0.1700

Data Index: 7794 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.3900. Min Act: -0.1700

Data Index: 530450 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.3587. Min Act: -0.1700

Data Index: 1194333 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.3744. Min Act: -0.1700

Data Index: 231978 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.3273. Min Act: -0.1700

Data Index: 919398 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 3.7033. Min Range: -3.7033

Max Act: 3.3430. Min Act: -0.1700

Data Index: 591551 (C4 (Web Text))

Max Activating Token Index: 693