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

Dataset: Open Web Text

Neuron 577 in Layer 3

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: 3.1001. Min Range: -3.1001

Max Act: 3.1001. Min Act: -0.1700

Data Index: 6715112 (Open Web Text)

Max Activating Token Index: 461

Text #1

Max Range: 3.1001. Min Range: -3.1001

Max Act: 3.0404. Min Act: -0.1700

Data Index: 3690328 (Open Web Text)

Max Activating Token Index: 611

Text #2

Max Range: 3.1001. Min Range: -3.1001

Max Act: 3.0377. Min Act: -0.1700

Data Index: 8577061 (Open Web Text)

Max Activating Token Index: 783

Text #3

Max Range: 3.1001. Min Range: -3.1001

Max Act: 3.0243. Min Act: -0.1700

Data Index: 2317362 (Open Web Text)

Max Activating Token Index: 272

Text #4

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9855. Min Act: -0.1700

Data Index: 2751949 (Open Web Text)

Max Activating Token Index: 353

Text #5

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9834. Min Act: -0.1700

Data Index: 6886607 (Open Web Text)

Max Activating Token Index: 631

Text #6

Max Range: 3.1001. Min Range: -3.1001

Max Act: 3.0056. Min Act: -0.1700

Data Index: 3259514 (Open Web Text)

Max Activating Token Index: 643

Text #7

Max Range: 3.1001. Min Range: -3.1001

Max Act: 3.0001. Min Act: -0.1700

Data Index: 4080299 (Open Web Text)

Max Activating Token Index: 464

Text #8

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9700. Min Act: -0.1700

Data Index: 5067693 (Open Web Text)

Max Activating Token Index: 565

Text #9

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9921. Min Act: -0.1700

Data Index: 5757833 (Open Web Text)

Max Activating Token Index: 245

Text #10

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9782. Min Act: -0.1700

Data Index: 4499285 (Open Web Text)

Max Activating Token Index: 596

Text #11

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9892. Min Act: -0.1700

Data Index: 2077987 (Open Web Text)

Max Activating Token Index: 733

Text #12

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9685. Min Act: -0.1700

Data Index: 6856001 (Open Web Text)

Max Activating Token Index: 405

Text #13

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9553. Min Act: -0.1700

Data Index: 3656929 (Open Web Text)

Max Activating Token Index: 400

Text #14

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9831. Min Act: -0.1700

Data Index: 1103432 (Open Web Text)

Max Activating Token Index: 782

Text #15

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9734. Min Act: -0.1700

Data Index: 5166652 (Open Web Text)

Max Activating Token Index: 431

Text #16

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9756. Min Act: -0.1700

Data Index: 4975755 (Open Web Text)

Max Activating Token Index: 898

Text #17

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9524. Min Act: -0.1700

Data Index: 8174286 (Open Web Text)

Max Activating Token Index: 390

Text #18

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9304. Min Act: -0.1700

Data Index: 334935 (Open Web Text)

Max Activating Token Index: 649

Text #19

Max Range: 3.1001. Min Range: -3.1001

Max Act: 2.9456. Min Act: -0.1700

Data Index: 6054468 (Open Web Text)

Max Activating Token Index: 351