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

Dataset: Open Web Text

Neuron 1219 in Layer 1

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: 1.9149. Min Range: -1.9149

Max Act: 1.9149. Min Act: -0.1700

Data Index: 52413 (Open Web Text)

Max Activating Token Index: 114

Text #1

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.8455. Min Act: -0.1700

Data Index: 6357118 (Open Web Text)

Max Activating Token Index: 63

Text #2

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.8351. Min Act: -0.1700

Data Index: 5562554 (Open Web Text)

Max Activating Token Index: 279

Text #3

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.8305. Min Act: -0.1700

Data Index: 4820291 (Open Web Text)

Max Activating Token Index: 761

Text #4

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7854. Min Act: -0.1700

Data Index: 752939 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7881. Min Act: -0.1700

Data Index: 5753618 (Open Web Text)

Max Activating Token Index: 263

Text #6

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7935. Min Act: -0.1700

Data Index: 5619239 (Open Web Text)

Max Activating Token Index: 317

Text #7

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7666. Min Act: -0.1700

Data Index: 6340630 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7560. Min Act: -0.1700

Data Index: 6474918 (Open Web Text)

Max Activating Token Index: 977

Text #9

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7626. Min Act: -0.1700

Data Index: 4826549 (Open Web Text)

Max Activating Token Index: 638

Text #10

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7587. Min Act: -0.1700

Data Index: 7164748 (Open Web Text)

Max Activating Token Index: 989

Text #11

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7585. Min Act: -0.1700

Data Index: 1413792 (Open Web Text)

Max Activating Token Index: 709

Text #12

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7714. Min Act: -0.1700

Data Index: 8809843 (Open Web Text)

Max Activating Token Index: 365

Text #13

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7544. Min Act: -0.1700

Data Index: 4672630 (Open Web Text)

Max Activating Token Index: 805

Text #14

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7450. Min Act: -0.1700

Data Index: 5532271 (Open Web Text)

Max Activating Token Index: 851

Text #15

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7412. Min Act: -0.1700

Data Index: 6335069 (Open Web Text)

Max Activating Token Index: 572

Text #16

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7331. Min Act: -0.1700

Data Index: 5152486 (Open Web Text)

Max Activating Token Index: 477

Text #17

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7428. Min Act: -0.1700

Data Index: 7467150 (Open Web Text)

Max Activating Token Index: 207

Text #18

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7324. Min Act: -0.1700

Data Index: 7504698 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.7433. Min Act: -0.1700

Data Index: 5132421 (Open Web Text)

Max Activating Token Index: 824