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

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

Neuron 562 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: 5.5531. Min Range: -5.5531

Max Act: 5.5531. Min Act: -0.1700

Data Index: 1234760 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.4593. Min Act: -0.1700

Data Index: 26651 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.3968. Min Act: -0.1700

Data Index: 378197 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.2718. Min Act: -0.1700

Data Index: 1070427 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.1468. Min Act: -0.1700

Data Index: 1222044 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.2093. Min Act: -0.1700

Data Index: 414880 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.3031. Min Act: -0.1700

Data Index: 850551 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.3031. Min Act: -0.1700

Data Index: 26012 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.1781. Min Act: -0.1700

Data Index: 511671 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.2093. Min Act: -0.1700

Data Index: 615844 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.1468. Min Act: -0.1700

Data Index: 51102 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.2093. Min Act: -0.1700

Data Index: 314 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.1781. Min Act: -0.1700

Data Index: 344350 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.1468. Min Act: -0.1700

Data Index: 1182697 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.1781. Min Act: -0.1700

Data Index: 497141 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.2718. Min Act: -0.1700

Data Index: 1161540 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.1156. Min Act: -0.1700

Data Index: 1120795 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.1156. Min Act: -0.1700

Data Index: 1030425 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.1468. Min Act: -0.1700

Data Index: 841253 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.1468. Min Act: -0.1700

Data Index: 323389 (C4 (Web Text))

Max Activating Token Index: 361