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

Dataset: Open Web Text

Neuron 521 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: 3.9505. Min Range: -3.9505

Max Act: 3.9505. Min Act: -0.1700

Data Index: 7574467 (Open Web Text)

Max Activating Token Index: 611

Text #1

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.8912. Min Act: -0.1700

Data Index: 8345238 (Open Web Text)

Max Activating Token Index: 435

Text #2

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.7631. Min Act: -0.1700

Data Index: 6297358 (Open Web Text)

Max Activating Token Index: 76

Text #3

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.7447. Min Act: -0.1700

Data Index: 4480749 (Open Web Text)

Max Activating Token Index: 196

Text #4

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.7540. Min Act: -0.1700

Data Index: 1933564 (Open Web Text)

Max Activating Token Index: 717

Text #5

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.7563. Min Act: -0.1700

Data Index: 4404356 (Open Web Text)

Max Activating Token Index: 48

Text #6

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.7083. Min Act: -0.1700

Data Index: 5715736 (Open Web Text)

Max Activating Token Index: 857

Text #7

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.7285. Min Act: -0.1700

Data Index: 5073593 (Open Web Text)

Max Activating Token Index: 773

Text #8

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.7227. Min Act: -0.1700

Data Index: 5586060 (Open Web Text)

Max Activating Token Index: 218

Text #9

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.6817. Min Act: -0.1700

Data Index: 4790454 (Open Web Text)

Max Activating Token Index: 430

Text #10

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.7071. Min Act: -0.1700

Data Index: 815247 (Open Web Text)

Max Activating Token Index: 685

Text #11

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.6940. Min Act: -0.1700

Data Index: 3341827 (Open Web Text)

Max Activating Token Index: 633

Text #12

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.6942. Min Act: -0.1700

Data Index: 6951493 (Open Web Text)

Max Activating Token Index: 788

Text #13

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.6848. Min Act: -0.1700

Data Index: 2358329 (Open Web Text)

Max Activating Token Index: 876

Text #14

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.6672. Min Act: -0.1700

Data Index: 2638022 (Open Web Text)

Max Activating Token Index: 451

Text #15

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.6626. Min Act: -0.1700

Data Index: 8664720 (Open Web Text)

Max Activating Token Index: 85

Text #16

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.6568. Min Act: -0.1700

Data Index: 8634307 (Open Web Text)

Max Activating Token Index: 687

Text #17

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.6626. Min Act: -0.1700

Data Index: 183736 (Open Web Text)

Max Activating Token Index: 279

Text #18

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.6603. Min Act: -0.1700

Data Index: 6891373 (Open Web Text)

Max Activating Token Index: 996

Text #19

Max Range: 3.9505. Min Range: -3.9505

Max Act: 3.6456. Min Act: -0.1700

Data Index: 1405398 (Open Web Text)

Max Activating Token Index: 480