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

Dataset: Open Web Text

Neuron 1699 in Layer 0

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: 1.4443. Min Range: -1.4443

Max Act: 1.4443. Min Act: -0.1586

Data Index: 8072949 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.4121. Min Act: -0.1636

Data Index: 8729500 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.4017. Min Act: -0.1638

Data Index: 5230239 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3902. Min Act: -0.1595

Data Index: 4277407 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3851. Min Act: -0.1541

Data Index: 5028477 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3876. Min Act: -0.1640

Data Index: 1385036 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3785. Min Act: -0.1477

Data Index: 1280164 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3709. Min Act: -0.1700

Data Index: 7355120 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3654. Min Act: -0.1641

Data Index: 7740062 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3709. Min Act: -0.1627

Data Index: 8185552 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3624. Min Act: -0.1547

Data Index: 3699412 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3603. Min Act: -0.1575

Data Index: 3187447 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3606. Min Act: -0.1645

Data Index: 3439386 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3590. Min Act: -0.1655

Data Index: 318693 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3530. Min Act: -0.1551

Data Index: 5484621 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3598. Min Act: -0.1685

Data Index: 1461592 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3507. Min Act: -0.1647

Data Index: 8024796 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3538. Min Act: -0.1589

Data Index: 3767955 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3492. Min Act: -0.1623

Data Index: 2552508 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3485. Min Act: -0.1628

Data Index: 4481440 (Open Web Text)

Max Activating Token Index: 3