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

Dataset: Open Web Text

Neuron 1078 in Layer 0

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: 3.6384. Min Range: -3.6384

Max Act: 3.6384. Min Act: -0.1700

Data Index: 5117054 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.6383. Min Act: -0.1700

Data Index: 4779413 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.6038. Min Act: -0.1700

Data Index: 7968423 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.6046. Min Act: -0.1700

Data Index: 4602507 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.6046. Min Act: -0.1700

Data Index: 2353435 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.6046. Min Act: -0.1700

Data Index: 4943479 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.6044. Min Act: -0.1700

Data Index: 7708569 (Open Web Text)

Max Activating Token Index: 33

Text #7

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.6046. Min Act: -0.1700

Data Index: 6920080 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.6046. Min Act: -0.1700

Data Index: 6348096 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.6046. Min Act: -0.1700

Data Index: 5563909 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.5588. Min Act: -0.1700

Data Index: 7725651 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.5724. Min Act: -0.1700

Data Index: 394621 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.5480. Min Act: -0.1700

Data Index: 7982150 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.5564. Min Act: -0.1700

Data Index: 2244701 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.5748. Min Act: -0.1700

Data Index: 391842 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.5588. Min Act: -0.1700

Data Index: 4634317 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.5217. Min Act: -0.1700

Data Index: 4864972 (Open Web Text)

Max Activating Token Index: 386

Text #17

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.5280. Min Act: -0.1700

Data Index: 4487760 (Open Web Text)

Max Activating Token Index: 933

Text #18

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.5418. Min Act: -0.1700

Data Index: 2043649 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.5199. Min Act: -0.1700

Data Index: 4565241 (Open Web Text)

Max Activating Token Index: 2