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

Dataset: Open Web Text

Neuron 1051 in Layer 0

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: 2.0181. Min Range: -2.0181

Max Act: 2.0181. Min Act: -0.1672

Data Index: 6470587 (Open Web Text)

Max Activating Token Index: 696

Text #1

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.9791. Min Act: -0.1700

Data Index: 780856 (Open Web Text)

Max Activating Token Index: 755

Text #2

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.9471. Min Act: -0.1640

Data Index: 5033994 (Open Web Text)

Max Activating Token Index: 985

Text #3

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.9366. Min Act: -0.1667

Data Index: 6628474 (Open Web Text)

Max Activating Token Index: 149

Text #4

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.9420. Min Act: -0.1700

Data Index: 7008842 (Open Web Text)

Max Activating Token Index: 1010

Text #5

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.9038. Min Act: -0.1700

Data Index: 7723683 (Open Web Text)

Max Activating Token Index: 565

Text #6

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8865. Min Act: -0.1662

Data Index: 865069 (Open Web Text)

Max Activating Token Index: 242

Text #7

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8885. Min Act: -0.1699

Data Index: 5213764 (Open Web Text)

Max Activating Token Index: 816

Text #8

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8884. Min Act: -0.1700

Data Index: 6087347 (Open Web Text)

Max Activating Token Index: 591

Text #9

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8666. Min Act: -0.1700

Data Index: 518679 (Open Web Text)

Max Activating Token Index: 106

Text #10

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8706. Min Act: -0.1699

Data Index: 2602292 (Open Web Text)

Max Activating Token Index: 613

Text #11

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8730. Min Act: -0.1686

Data Index: 566814 (Open Web Text)

Max Activating Token Index: 133

Text #12

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8648. Min Act: -0.1661

Data Index: 3518692 (Open Web Text)

Max Activating Token Index: 374

Text #13

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8613. Min Act: -0.1690

Data Index: 3808581 (Open Web Text)

Max Activating Token Index: 902

Text #14

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8488. Min Act: -0.1695

Data Index: 1165651 (Open Web Text)

Max Activating Token Index: 315

Text #15

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8551. Min Act: -0.1677

Data Index: 6652751 (Open Web Text)

Max Activating Token Index: 848

Text #16

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8501. Min Act: -0.1699

Data Index: 4647357 (Open Web Text)

Max Activating Token Index: 800

Text #17

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8444. Min Act: -0.1671

Data Index: 1255176 (Open Web Text)

Max Activating Token Index: 735

Text #18

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8458. Min Act: -0.1691

Data Index: 5805707 (Open Web Text)

Max Activating Token Index: 762

Text #19

Max Range: 2.0181. Min Range: -2.0181

Max Act: 1.8359. Min Act: -0.1672

Data Index: 1921938 (Open Web Text)

Max Activating Token Index: 393