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

Dataset: Open Web Text

Neuron 54 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: 3.8321. Min Range: -3.8321

Max Act: 3.8321. Min Act: -0.1700

Data Index: 1370492 (Open Web Text)

Max Activating Token Index: 370

Text #1

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.8320. Min Act: -0.1700

Data Index: 8318380 (Open Web Text)

Max Activating Token Index: 289

Text #2

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.6503. Min Act: -0.1700

Data Index: 4941090 (Open Web Text)

Max Activating Token Index: 771

Text #3

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.6860. Min Act: -0.1700

Data Index: 2731095 (Open Web Text)

Max Activating Token Index: 852

Text #4

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.6760. Min Act: -0.1700

Data Index: 7735795 (Open Web Text)

Max Activating Token Index: 608

Text #5

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.6610. Min Act: -0.1700

Data Index: 4808704 (Open Web Text)

Max Activating Token Index: 551

Text #6

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5968. Min Act: -0.1700

Data Index: 7522851 (Open Web Text)

Max Activating Token Index: 539

Text #7

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.6187. Min Act: -0.1700

Data Index: 8720291 (Open Web Text)

Max Activating Token Index: 42

Text #8

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5970. Min Act: -0.1700

Data Index: 1676305 (Open Web Text)

Max Activating Token Index: 258

Text #9

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5851. Min Act: -0.1700

Data Index: 7120608 (Open Web Text)

Max Activating Token Index: 967

Text #10

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5546. Min Act: -0.1700

Data Index: 993954 (Open Web Text)

Max Activating Token Index: 594

Text #11

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5425. Min Act: -0.1700

Data Index: 5382069 (Open Web Text)

Max Activating Token Index: 596

Text #12

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5497. Min Act: -0.1700

Data Index: 1943602 (Open Web Text)

Max Activating Token Index: 330

Text #13

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5825. Min Act: -0.1700

Data Index: 4480137 (Open Web Text)

Max Activating Token Index: 761

Text #14

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5755. Min Act: -0.1700

Data Index: 7479470 (Open Web Text)

Max Activating Token Index: 355

Text #15

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5680. Min Act: -0.1700

Data Index: 8202471 (Open Web Text)

Max Activating Token Index: 697

Text #16

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5681. Min Act: -0.1700

Data Index: 4000436 (Open Web Text)

Max Activating Token Index: 930

Text #17

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5517. Min Act: -0.1700

Data Index: 4303457 (Open Web Text)

Max Activating Token Index: 233

Text #18

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5616. Min Act: -0.1700

Data Index: 4303454 (Open Web Text)

Max Activating Token Index: 610

Text #19

Max Range: 3.8321. Min Range: -3.8321

Max Act: 3.5765. Min Act: -0.1700

Data Index: 5813279 (Open Web Text)

Max Activating Token Index: 134