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

Dataset: Open Web Text

Neuron 2440 in Layer 5

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: 4.0203. Min Range: -4.0203

Max Act: 4.0028. Min Act: -0.1700

Data Index: 7930094 (Open Web Text)

Max Activating Token Index: 729

Text #1

Max Range: 4.0203. Min Range: -4.0203

Max Act: 4.0203. Min Act: -0.1700

Data Index: 4266174 (Open Web Text)

Max Activating Token Index: 232

Text #2

Max Range: 4.0203. Min Range: -4.0203

Max Act: 4.0011. Min Act: -0.1700

Data Index: 1574893 (Open Web Text)

Max Activating Token Index: 928

Text #3

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.9978. Min Act: -0.1700

Data Index: 1713771 (Open Web Text)

Max Activating Token Index: 914

Text #4

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.9566. Min Act: -0.1700

Data Index: 48633 (Open Web Text)

Max Activating Token Index: 456

Text #5

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.9483. Min Act: -0.1700

Data Index: 117593 (Open Web Text)

Max Activating Token Index: 100

Text #6

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.9651. Min Act: -0.1700

Data Index: 5597475 (Open Web Text)

Max Activating Token Index: 494

Text #7

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.9129. Min Act: -0.1700

Data Index: 2826843 (Open Web Text)

Max Activating Token Index: 52

Text #8

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.9547. Min Act: -0.1700

Data Index: 171184 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.8582. Min Act: -0.1700

Data Index: 5970401 (Open Web Text)

Max Activating Token Index: 388

Text #10

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.8533. Min Act: -0.1700

Data Index: 735463 (Open Web Text)

Max Activating Token Index: 572

Text #11

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.8978. Min Act: -0.1700

Data Index: 3975444 (Open Web Text)

Max Activating Token Index: 958

Text #12

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.9056. Min Act: -0.1700

Data Index: 5560606 (Open Web Text)

Max Activating Token Index: 545

Text #13

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.9046. Min Act: -0.1700

Data Index: 475109 (Open Web Text)

Max Activating Token Index: 867

Text #14

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.8452. Min Act: -0.1700

Data Index: 5982210 (Open Web Text)

Max Activating Token Index: 620

Text #15

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.8608. Min Act: -0.1700

Data Index: 1986961 (Open Web Text)

Max Activating Token Index: 693

Text #16

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.8565. Min Act: -0.1700

Data Index: 5709390 (Open Web Text)

Max Activating Token Index: 286

Text #17

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.8682. Min Act: -0.1700

Data Index: 4320442 (Open Web Text)

Max Activating Token Index: 43

Text #18

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.8770. Min Act: -0.1700

Data Index: 475111 (Open Web Text)

Max Activating Token Index: 702

Text #19

Max Range: 4.0203. Min Range: -4.0203

Max Act: 3.8477. Min Act: -0.1700

Data Index: 6760655 (Open Web Text)

Max Activating Token Index: 324