Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1413 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.5971. Min Range: -7.5971

Max Act: 7.5971. Min Act: -0.1700

Data Index: 721406 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.4721. Min Act: -0.1700

Data Index: 402506 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.9096. Min Act: -0.1700

Data Index: 34315 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.9096. Min Act: -0.1700

Data Index: 890801 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.9096. Min Act: -0.1700

Data Index: 332874 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.9096. Min Act: -0.1700

Data Index: 1232151 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.8471. Min Act: -0.1700

Data Index: 173130 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.9096. Min Act: -0.1700

Data Index: 912718 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.8471. Min Act: -0.1700

Data Index: 392586 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.7846. Min Act: -0.1700

Data Index: 836598 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.8471. Min Act: -0.1700

Data Index: 734530 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.7846. Min Act: -0.1700

Data Index: 146222 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.5033. Min Act: -0.1700

Data Index: 403420 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.7533. Min Act: -0.1700

Data Index: 882264 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.6908. Min Act: -0.1700

Data Index: 885012 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.8471. Min Act: -0.1700

Data Index: 365864 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.7846. Min Act: -0.1700

Data Index: 238438 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.6908. Min Act: -0.1700

Data Index: 493574 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.5033. Min Act: -0.1700

Data Index: 456580 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 7.5971. Min Range: -7.5971

Max Act: 6.6908. Min Act: -0.1700

Data Index: 799536 (C4 (Web Text))

Max Activating Token Index: 575