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

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

Neuron 1264 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.9310. Min Act: -0.1700

Data Index: 200395 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.8372. Min Act: -0.1700

Data Index: 1158652 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.7746. Min Act: -0.1700

Data Index: 928254 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.7746. Min Act: -0.1700

Data Index: 1232927 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.7746. Min Act: -0.1700

Data Index: 654980 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.7433. Min Act: -0.1700

Data Index: 52409 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.7433. Min Act: -0.1700

Data Index: 723198 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.7121. Min Act: -0.1700

Data Index: 1051185 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.7121. Min Act: -0.1700

Data Index: 849321 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.6808. Min Act: -0.1700

Data Index: 724121 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.6808. Min Act: -0.1700

Data Index: 245528 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.6808. Min Act: -0.1700

Data Index: 1002959 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.6808. Min Act: -0.1700

Data Index: 970035 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.6495. Min Act: -0.1700

Data Index: 639071 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.6181. Min Act: -0.1700

Data Index: 1065084 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.6495. Min Act: -0.1700

Data Index: 840977 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.6495. Min Act: -0.1700

Data Index: 1129895 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.6181. Min Act: -0.1700

Data Index: 1091366 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.6495. Min Act: -0.1700

Data Index: 986971 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 3.9310. Min Range: -3.9310

Max Act: 3.5868. Min Act: -0.1700

Data Index: 511855 (C4 (Web Text))

Max Activating Token Index: 310