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

Dataset: Open Web Text

Neuron 2824 in Layer 6

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: 3.8997. Min Range: -3.8997

Max Act: 3.8997. Min Act: -0.1700

Data Index: 7136355 (Open Web Text)

Max Activating Token Index: 395

Text #1

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.8927. Min Act: -0.1700

Data Index: 5198646 (Open Web Text)

Max Activating Token Index: 298

Text #2

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.8461. Min Act: -0.1700

Data Index: 1369459 (Open Web Text)

Max Activating Token Index: 767

Text #3

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.8248. Min Act: -0.1700

Data Index: 242164 (Open Web Text)

Max Activating Token Index: 957

Text #4

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.8339. Min Act: -0.1700

Data Index: 1369460 (Open Web Text)

Max Activating Token Index: 70

Text #5

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.8250. Min Act: -0.1700

Data Index: 8036822 (Open Web Text)

Max Activating Token Index: 440

Text #6

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.8106. Min Act: -0.1700

Data Index: 2869861 (Open Web Text)

Max Activating Token Index: 494

Text #7

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.8124. Min Act: -0.1700

Data Index: 2683121 (Open Web Text)

Max Activating Token Index: 69

Text #8

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7986. Min Act: -0.1700

Data Index: 7683869 (Open Web Text)

Max Activating Token Index: 557

Text #9

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7722. Min Act: -0.1700

Data Index: 14201 (Open Web Text)

Max Activating Token Index: 762

Text #10

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7601. Min Act: -0.1700

Data Index: 3358535 (Open Web Text)

Max Activating Token Index: 381

Text #11

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7545. Min Act: -0.1700

Data Index: 3558543 (Open Web Text)

Max Activating Token Index: 1016

Text #12

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7710. Min Act: -0.1700

Data Index: 6605886 (Open Web Text)

Max Activating Token Index: 421

Text #13

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7615. Min Act: -0.1700

Data Index: 4471210 (Open Web Text)

Max Activating Token Index: 605

Text #14

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7527. Min Act: -0.1700

Data Index: 5271223 (Open Web Text)

Max Activating Token Index: 665

Text #15

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7438. Min Act: -0.1700

Data Index: 5847684 (Open Web Text)

Max Activating Token Index: 680

Text #16

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7562. Min Act: -0.1700

Data Index: 5039554 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7383. Min Act: -0.1700

Data Index: 3987127 (Open Web Text)

Max Activating Token Index: 492

Text #18

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7579. Min Act: -0.1700

Data Index: 2401743 (Open Web Text)

Max Activating Token Index: 345

Text #19

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7454. Min Act: -0.1700

Data Index: 6759044 (Open Web Text)

Max Activating Token Index: 584