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

Dataset: Open Web Text

Neuron 963 in Layer 4

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: 3.2651. Min Range: -3.2651

Max Act: 3.2651. Min Act: -0.1700

Data Index: 4953517 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.2646. Min Act: -0.1700

Data Index: 6117882 (Open Web Text)

Max Activating Token Index: 477

Text #2

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.2479. Min Act: -0.1700

Data Index: 1684510 (Open Web Text)

Max Activating Token Index: 1017

Text #3

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.2488. Min Act: -0.1700

Data Index: 7495825 (Open Web Text)

Max Activating Token Index: 377

Text #4

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.2470. Min Act: -0.1700

Data Index: 4439320 (Open Web Text)

Max Activating Token Index: 977

Text #5

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1810. Min Act: -0.1700

Data Index: 619618 (Open Web Text)

Max Activating Token Index: 578

Text #6

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1725. Min Act: -0.1700

Data Index: 1537107 (Open Web Text)

Max Activating Token Index: 649

Text #7

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.2005. Min Act: -0.1700

Data Index: 2040185 (Open Web Text)

Max Activating Token Index: 1017

Text #8

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1916. Min Act: -0.1700

Data Index: 2459178 (Open Web Text)

Max Activating Token Index: 84

Text #9

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1609. Min Act: -0.1700

Data Index: 3782359 (Open Web Text)

Max Activating Token Index: 995

Text #10

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1720. Min Act: -0.1700

Data Index: 145332 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1527. Min Act: -0.1700

Data Index: 1182630 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1438. Min Act: -0.1700

Data Index: 6471355 (Open Web Text)

Max Activating Token Index: 897

Text #13

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1623. Min Act: -0.1700

Data Index: 6590578 (Open Web Text)

Max Activating Token Index: 927

Text #14

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1512. Min Act: -0.1700

Data Index: 4281045 (Open Web Text)

Max Activating Token Index: 693

Text #15

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1408. Min Act: -0.1700

Data Index: 3675744 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1466. Min Act: -0.1700

Data Index: 216991 (Open Web Text)

Max Activating Token Index: 323

Text #17

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1394. Min Act: -0.1700

Data Index: 5130218 (Open Web Text)

Max Activating Token Index: 383

Text #18

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1214. Min Act: -0.1700

Data Index: 5885897 (Open Web Text)

Max Activating Token Index: 684

Text #19

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1482. Min Act: -0.1700

Data Index: 5482236 (Open Web Text)

Max Activating Token Index: 566