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

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

Neuron 818 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.5547. Min Act: -0.1700

Data Index: 632989 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.3360. Min Act: -0.1700

Data Index: 956303 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.3047. Min Act: -0.1700

Data Index: 786943 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.2422. Min Act: -0.1700

Data Index: 834013 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.1485. Min Act: -0.1700

Data Index: 457447 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.0235. Min Act: -0.1700

Data Index: 449858 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.0860. Min Act: -0.1700

Data Index: 1037873 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.0547. Min Act: -0.1700

Data Index: 1047583 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.0860. Min Act: -0.1700

Data Index: 46580 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.0860. Min Act: -0.1700

Data Index: 724981 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.0860. Min Act: -0.1700

Data Index: 535997 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.0547. Min Act: -0.1700

Data Index: 891651 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.9297. Min Act: -0.1700

Data Index: 853765 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.0235. Min Act: -0.1697

Data Index: 659820 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.0235. Min Act: -0.1700

Data Index: 476380 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.9922. Min Act: -0.1700

Data Index: 372138 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.9922. Min Act: -0.1700

Data Index: 510938 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.0235. Min Act: -0.1700

Data Index: 959477 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.9922. Min Act: -0.1700

Data Index: 875797 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.9922. Min Act: -0.1700

Data Index: 616124 (C4 (Web Text))

Max Activating Token Index: 410