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

Dataset: Open Web Text

Neuron 1808 in Layer 6

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: 3.8963. Min Range: -3.8963

Max Act: 3.8963. Min Act: -0.1700

Data Index: 8143088 (Open Web Text)

Max Activating Token Index: 511

Text #1

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.7759. Min Act: -0.1700

Data Index: 7480605 (Open Web Text)

Max Activating Token Index: 294

Text #2

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.7932. Min Act: -0.1700

Data Index: 2694290 (Open Web Text)

Max Activating Token Index: 280

Text #3

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.7783. Min Act: -0.1700

Data Index: 5231241 (Open Web Text)

Max Activating Token Index: 940

Text #4

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.8065. Min Act: -0.1700

Data Index: 718131 (Open Web Text)

Max Activating Token Index: 785

Text #5

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.8017. Min Act: -0.1700

Data Index: 8515104 (Open Web Text)

Max Activating Token Index: 615

Text #6

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.7134. Min Act: -0.1700

Data Index: 3693576 (Open Web Text)

Max Activating Token Index: 417

Text #7

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.6978. Min Act: -0.1700

Data Index: 2917000 (Open Web Text)

Max Activating Token Index: 976

Text #8

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.7080. Min Act: -0.1700

Data Index: 4172998 (Open Web Text)

Max Activating Token Index: 183

Text #9

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.6902. Min Act: -0.1700

Data Index: 2662477 (Open Web Text)

Max Activating Token Index: 644

Text #10

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.6822. Min Act: -0.1700

Data Index: 5479294 (Open Web Text)

Max Activating Token Index: 405

Text #11

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.6790. Min Act: -0.1700

Data Index: 4822090 (Open Web Text)

Max Activating Token Index: 1001

Text #12

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.6686. Min Act: -0.1700

Data Index: 4495360 (Open Web Text)

Max Activating Token Index: 303

Text #13

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.6412. Min Act: -0.1700

Data Index: 5608367 (Open Web Text)

Max Activating Token Index: 421

Text #14

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.6382. Min Act: -0.1700

Data Index: 5924651 (Open Web Text)

Max Activating Token Index: 914

Text #15

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.6371. Min Act: -0.1700

Data Index: 5220523 (Open Web Text)

Max Activating Token Index: 696

Text #16

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.6207. Min Act: -0.1700

Data Index: 1274514 (Open Web Text)

Max Activating Token Index: 744

Text #17

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.6240. Min Act: -0.1700

Data Index: 4471837 (Open Web Text)

Max Activating Token Index: 898

Text #18

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.6155. Min Act: -0.1700

Data Index: 6648981 (Open Web Text)

Max Activating Token Index: 677

Text #19

Max Range: 3.8963. Min Range: -3.8963

Max Act: 3.6098. Min Act: -0.1700

Data Index: 4518134 (Open Web Text)

Max Activating Token Index: 555