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

Dataset: Open Web Text

Neuron 1299 in Layer 3

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: 4.7040. Min Range: -4.7040

Max Act: 4.7040. Min Act: -0.1700

Data Index: 8779471 (Open Web Text)

Max Activating Token Index: 577

Text #1

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.6661. Min Act: -0.1700

Data Index: 8171623 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.6112. Min Act: -0.1700

Data Index: 7195045 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.6009. Min Act: -0.1700

Data Index: 3577561 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5723. Min Act: -0.1700

Data Index: 6490364 (Open Web Text)

Max Activating Token Index: 593

Text #5

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5740. Min Act: -0.1700

Data Index: 4844041 (Open Web Text)

Max Activating Token Index: 818

Text #6

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.6261. Min Act: -0.1700

Data Index: 8184210 (Open Web Text)

Max Activating Token Index: 822

Text #7

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.6360. Min Act: -0.1700

Data Index: 2113525 (Open Web Text)

Max Activating Token Index: 620

Text #8

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5600. Min Act: -0.1700

Data Index: 3337779 (Open Web Text)

Max Activating Token Index: 532

Text #9

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5394. Min Act: -0.1700

Data Index: 2403836 (Open Web Text)

Max Activating Token Index: 310

Text #10

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5799. Min Act: -0.1700

Data Index: 8679361 (Open Web Text)

Max Activating Token Index: 900

Text #11

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5092. Min Act: -0.1700

Data Index: 3705137 (Open Web Text)

Max Activating Token Index: 509

Text #12

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5141. Min Act: -0.1700

Data Index: 6787653 (Open Web Text)

Max Activating Token Index: 468

Text #13

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5312. Min Act: -0.1700

Data Index: 6286737 (Open Web Text)

Max Activating Token Index: 404

Text #14

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5129. Min Act: -0.1700

Data Index: 3878548 (Open Web Text)

Max Activating Token Index: 943

Text #15

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5564. Min Act: -0.1700

Data Index: 3821066 (Open Web Text)

Max Activating Token Index: 105

Text #16

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5332. Min Act: -0.1700

Data Index: 2795926 (Open Web Text)

Max Activating Token Index: 91

Text #17

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5413. Min Act: -0.1700

Data Index: 8114311 (Open Web Text)

Max Activating Token Index: 81

Text #18

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5188. Min Act: -0.1700

Data Index: 4621020 (Open Web Text)

Max Activating Token Index: 545

Text #19

Max Range: 4.7040. Min Range: -4.7040

Max Act: 4.5615. Min Act: -0.1700

Data Index: 7175550 (Open Web Text)

Max Activating Token Index: 365