Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1626 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.6632. Min Act: -0.1700

Data Index: 1479739 (Open Web Text)

Max Activating Token Index: 327

Text #1

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.6044. Min Act: -0.1700

Data Index: 7301179 (Open Web Text)

Max Activating Token Index: 785

Text #2

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.5536. Min Act: -0.1700

Data Index: 3869010 (Open Web Text)

Max Activating Token Index: 827

Text #3

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.5646. Min Act: -0.1700

Data Index: 7379557 (Open Web Text)

Max Activating Token Index: 49

Text #4

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.5268. Min Act: -0.1700

Data Index: 2537711 (Open Web Text)

Max Activating Token Index: 339

Text #5

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.5512. Min Act: -0.1700

Data Index: 7461506 (Open Web Text)

Max Activating Token Index: 905

Text #6

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.5158. Min Act: -0.1700

Data Index: 7748178 (Open Web Text)

Max Activating Token Index: 612

Text #7

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.5056. Min Act: -0.1700

Data Index: 3408667 (Open Web Text)

Max Activating Token Index: 1000

Text #8

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.4929. Min Act: -0.1700

Data Index: 8116767 (Open Web Text)

Max Activating Token Index: 43

Text #9

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.5130. Min Act: -0.1700

Data Index: 5872654 (Open Web Text)

Max Activating Token Index: 568

Text #10

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.4681. Min Act: -0.1700

Data Index: 1101627 (Open Web Text)

Max Activating Token Index: 190

Text #11

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.4522. Min Act: -0.1700

Data Index: 4339818 (Open Web Text)

Max Activating Token Index: 81

Text #12

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.4677. Min Act: -0.1700

Data Index: 1517081 (Open Web Text)

Max Activating Token Index: 181

Text #13

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.4679. Min Act: -0.1700

Data Index: 6817383 (Open Web Text)

Max Activating Token Index: 857

Text #14

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.4836. Min Act: -0.1700

Data Index: 5353710 (Open Web Text)

Max Activating Token Index: 372

Text #15

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.5302. Min Act: -0.1700

Data Index: 951506 (Open Web Text)

Max Activating Token Index: 565

Text #16

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.4716. Min Act: -0.1700

Data Index: 4693390 (Open Web Text)

Max Activating Token Index: 947

Text #17

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.4498. Min Act: -0.1700

Data Index: 7225984 (Open Web Text)

Max Activating Token Index: 680

Text #18

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.4763. Min Act: -0.1700

Data Index: 5457772 (Open Web Text)

Max Activating Token Index: 946

Text #19

Max Range: 2.6632. Min Range: -2.6632

Max Act: 2.4589. Min Act: -0.1700

Data Index: 6038024 (Open Web Text)

Max Activating Token Index: 360