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

Dataset: Open Web Text

Neuron 894 in Layer 6

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: 4.0406. Min Range: -4.0406

Max Act: 4.0122. Min Act: -0.1700

Data Index: 8228779 (Open Web Text)

Max Activating Token Index: 219

Text #1

Max Range: 4.0406. Min Range: -4.0406

Max Act: 4.0406. Min Act: -0.1700

Data Index: 1353609 (Open Web Text)

Max Activating Token Index: 423

Text #2

Max Range: 4.0406. Min Range: -4.0406

Max Act: 4.0084. Min Act: -0.1700

Data Index: 4851396 (Open Web Text)

Max Activating Token Index: 931

Text #3

Max Range: 4.0406. Min Range: -4.0406

Max Act: 4.0145. Min Act: -0.1700

Data Index: 5959386 (Open Web Text)

Max Activating Token Index: 877

Text #4

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9938. Min Act: -0.1700

Data Index: 6876140 (Open Web Text)

Max Activating Token Index: 613

Text #5

Max Range: 4.0406. Min Range: -4.0406

Max Act: 4.0039. Min Act: -0.1700

Data Index: 1954690 (Open Web Text)

Max Activating Token Index: 973

Text #6

Max Range: 4.0406. Min Range: -4.0406

Max Act: 4.0215. Min Act: -0.1700

Data Index: 1042869 (Open Web Text)

Max Activating Token Index: 423

Text #7

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9824. Min Act: -0.1700

Data Index: 2648851 (Open Web Text)

Max Activating Token Index: 993

Text #8

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9866. Min Act: -0.1700

Data Index: 81187 (Open Web Text)

Max Activating Token Index: 856

Text #9

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9685. Min Act: -0.1700

Data Index: 255037 (Open Web Text)

Max Activating Token Index: 559

Text #10

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9672. Min Act: -0.1700

Data Index: 1353620 (Open Web Text)

Max Activating Token Index: 183

Text #11

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9511. Min Act: -0.1700

Data Index: 2695505 (Open Web Text)

Max Activating Token Index: 688

Text #12

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9345. Min Act: -0.1700

Data Index: 2583674 (Open Web Text)

Max Activating Token Index: 714

Text #13

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9617. Min Act: -0.1700

Data Index: 4131717 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9311. Min Act: -0.1700

Data Index: 3107026 (Open Web Text)

Max Activating Token Index: 461

Text #15

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9135. Min Act: -0.1700

Data Index: 1649948 (Open Web Text)

Max Activating Token Index: 291

Text #16

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9300. Min Act: -0.1700

Data Index: 915215 (Open Web Text)

Max Activating Token Index: 954

Text #17

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9199. Min Act: -0.1700

Data Index: 8304918 (Open Web Text)

Max Activating Token Index: 833

Text #18

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9117. Min Act: -0.1700

Data Index: 1478073 (Open Web Text)

Max Activating Token Index: 975

Text #19

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.9101. Min Act: -0.1700

Data Index: 2246879 (Open Web Text)

Max Activating Token Index: 814