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

Dataset: Open Web Text

Neuron 319 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: 4.8740. Min Range: -4.8740

Max Act: 4.8740. Min Act: -0.1700

Data Index: 6511357 (Open Web Text)

Max Activating Token Index: 623

Text #1

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.7665. Min Act: -0.1700

Data Index: 6071650 (Open Web Text)

Max Activating Token Index: 372

Text #2

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.7634. Min Act: -0.1700

Data Index: 2092230 (Open Web Text)

Max Activating Token Index: 958

Text #3

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.7324. Min Act: -0.1700

Data Index: 8049643 (Open Web Text)

Max Activating Token Index: 397

Text #4

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.6871. Min Act: -0.1700

Data Index: 101337 (Open Web Text)

Max Activating Token Index: 998

Text #5

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.6855. Min Act: -0.1700

Data Index: 7474058 (Open Web Text)

Max Activating Token Index: 613

Text #6

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.6563. Min Act: -0.1700

Data Index: 7249029 (Open Web Text)

Max Activating Token Index: 411

Text #7

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.6495. Min Act: -0.1700

Data Index: 5566559 (Open Web Text)

Max Activating Token Index: 887

Text #8

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.6268. Min Act: -0.1700

Data Index: 7559385 (Open Web Text)

Max Activating Token Index: 203

Text #9

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.6115. Min Act: -0.1700

Data Index: 7114830 (Open Web Text)

Max Activating Token Index: 622

Text #10

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.6230. Min Act: -0.1700

Data Index: 130579 (Open Web Text)

Max Activating Token Index: 904

Text #11

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.5599. Min Act: -0.1700

Data Index: 3263529 (Open Web Text)

Max Activating Token Index: 40

Text #12

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.6079. Min Act: -0.1700

Data Index: 3640133 (Open Web Text)

Max Activating Token Index: 130

Text #13

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.5873. Min Act: -0.1700

Data Index: 66035 (Open Web Text)

Max Activating Token Index: 334

Text #14

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.5562. Min Act: -0.1700

Data Index: 8355778 (Open Web Text)

Max Activating Token Index: 684

Text #15

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.5445. Min Act: -0.1700

Data Index: 7908421 (Open Web Text)

Max Activating Token Index: 393

Text #16

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.5329. Min Act: -0.1700

Data Index: 7870757 (Open Web Text)

Max Activating Token Index: 72

Text #17

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.5187. Min Act: -0.1700

Data Index: 5132096 (Open Web Text)

Max Activating Token Index: 979

Text #18

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.5348. Min Act: -0.1700

Data Index: 4701601 (Open Web Text)

Max Activating Token Index: 859

Text #19

Max Range: 4.8740. Min Range: -4.8740

Max Act: 4.5420. Min Act: -0.1700

Data Index: 4064717 (Open Web Text)

Max Activating Token Index: 996