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

Dataset: Open Web Text

Neuron 2382 in Layer 2

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: 4.0712. Min Range: -4.0712

Max Act: 4.0526. Min Act: -0.1700

Data Index: 8626996 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 4.0712. Min Range: -4.0712

Max Act: 4.0712. Min Act: -0.1700

Data Index: 4747412 (Open Web Text)

Max Activating Token Index: 461

Text #2

Max Range: 4.0712. Min Range: -4.0712

Max Act: 4.0349. Min Act: -0.1700

Data Index: 8572706 (Open Web Text)

Max Activating Token Index: 522

Text #3

Max Range: 4.0712. Min Range: -4.0712

Max Act: 4.0208. Min Act: -0.1700

Data Index: 717922 (Open Web Text)

Max Activating Token Index: 741

Text #4

Max Range: 4.0712. Min Range: -4.0712

Max Act: 4.0230. Min Act: -0.1700

Data Index: 4990434 (Open Web Text)

Max Activating Token Index: 603

Text #5

Max Range: 4.0712. Min Range: -4.0712

Max Act: 4.0533. Min Act: -0.1700

Data Index: 2193242 (Open Web Text)

Max Activating Token Index: 337

Text #6

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.9469. Min Act: -0.1700

Data Index: 4433021 (Open Web Text)

Max Activating Token Index: 210

Text #7

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.9701. Min Act: -0.1700

Data Index: 2084299 (Open Web Text)

Max Activating Token Index: 324

Text #8

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.9046. Min Act: -0.1700

Data Index: 4640138 (Open Web Text)

Max Activating Token Index: 609

Text #9

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.9041. Min Act: -0.1700

Data Index: 50928 (Open Web Text)

Max Activating Token Index: 538

Text #10

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.9218. Min Act: -0.1700

Data Index: 8275458 (Open Web Text)

Max Activating Token Index: 879

Text #11

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.9195. Min Act: -0.1700

Data Index: 571573 (Open Web Text)

Max Activating Token Index: 29

Text #12

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.9134. Min Act: -0.1700

Data Index: 3896386 (Open Web Text)

Max Activating Token Index: 522

Text #13

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.8679. Min Act: -0.1700

Data Index: 4374845 (Open Web Text)

Max Activating Token Index: 423

Text #14

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.8432. Min Act: -0.1700

Data Index: 7260653 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.8661. Min Act: -0.1700

Data Index: 4100589 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.8749. Min Act: -0.1700

Data Index: 3911902 (Open Web Text)

Max Activating Token Index: 691

Text #17

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.9096. Min Act: -0.1700

Data Index: 2057142 (Open Web Text)

Max Activating Token Index: 391

Text #18

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.7520. Min Act: -0.1700

Data Index: 1441550 (Open Web Text)

Max Activating Token Index: 378

Text #19

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.8633. Min Act: -0.1700

Data Index: 7027104 (Open Web Text)

Max Activating Token Index: 429