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

Dataset: Open Web Text

Neuron 2943 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: 4.8298. Min Range: -4.8298

Max Act: 4.8298. Min Act: -0.1700

Data Index: 3976377 (Open Web Text)

Max Activating Token Index: 422

Text #1

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.7821. Min Act: -0.1700

Data Index: 6549555 (Open Web Text)

Max Activating Token Index: 253

Text #2

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.7907. Min Act: -0.1700

Data Index: 8626054 (Open Web Text)

Max Activating Token Index: 323

Text #3

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.8029. Min Act: -0.1700

Data Index: 2427000 (Open Web Text)

Max Activating Token Index: 333

Text #4

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.7321. Min Act: -0.1700

Data Index: 3516753 (Open Web Text)

Max Activating Token Index: 873

Text #5

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.7482. Min Act: -0.1700

Data Index: 3160223 (Open Web Text)

Max Activating Token Index: 481

Text #6

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.7541. Min Act: -0.1700

Data Index: 3936050 (Open Web Text)

Max Activating Token Index: 603

Text #7

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.7059. Min Act: -0.1700

Data Index: 3079514 (Open Web Text)

Max Activating Token Index: 926

Text #8

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.7148. Min Act: -0.1700

Data Index: 6257485 (Open Web Text)

Max Activating Token Index: 810

Text #9

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6944. Min Act: -0.1700

Data Index: 5793524 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6631. Min Act: -0.1700

Data Index: 6941851 (Open Web Text)

Max Activating Token Index: 849

Text #11

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6705. Min Act: -0.1700

Data Index: 1161594 (Open Web Text)

Max Activating Token Index: 321

Text #12

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6631. Min Act: -0.1700

Data Index: 2125547 (Open Web Text)

Max Activating Token Index: 893

Text #13

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6643. Min Act: -0.1700

Data Index: 7089982 (Open Web Text)

Max Activating Token Index: 787

Text #14

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6264. Min Act: -0.1700

Data Index: 5385405 (Open Web Text)

Max Activating Token Index: 341

Text #15

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6293. Min Act: -0.1700

Data Index: 6941847 (Open Web Text)

Max Activating Token Index: 409

Text #16

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6668. Min Act: -0.1700

Data Index: 5566866 (Open Web Text)

Max Activating Token Index: 150

Text #17

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6351. Min Act: -0.1700

Data Index: 5243585 (Open Web Text)

Max Activating Token Index: 577

Text #18

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6422. Min Act: -0.1700

Data Index: 6549554 (Open Web Text)

Max Activating Token Index: 191

Text #19

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.5955. Min Act: -0.1700

Data Index: 4349856 (Open Web Text)

Max Activating Token Index: 404