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

Dataset: Open Web Text

Neuron 2713 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: 3.8175. Min Range: -3.8175

Max Act: 3.8175. Min Act: -0.1700

Data Index: 4595959 (Open Web Text)

Max Activating Token Index: 392

Text #1

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7462. Min Act: -0.1700

Data Index: 6948986 (Open Web Text)

Max Activating Token Index: 222

Text #2

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7434. Min Act: -0.1700

Data Index: 4635405 (Open Web Text)

Max Activating Token Index: 521

Text #3

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7812. Min Act: -0.1700

Data Index: 4635404 (Open Web Text)

Max Activating Token Index: 361

Text #4

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7566. Min Act: -0.1700

Data Index: 4595960 (Open Web Text)

Max Activating Token Index: 306

Text #5

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7700. Min Act: -0.1700

Data Index: 2354259 (Open Web Text)

Max Activating Token Index: 197

Text #6

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.6504. Min Act: -0.1700

Data Index: 4595958 (Open Web Text)

Max Activating Token Index: 874

Text #7

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.6437. Min Act: -0.1700

Data Index: 6948989 (Open Web Text)

Max Activating Token Index: 750

Text #8

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.6176. Min Act: -0.1700

Data Index: 3657386 (Open Web Text)

Max Activating Token Index: 562

Text #9

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.6460. Min Act: -0.1700

Data Index: 4635406 (Open Web Text)

Max Activating Token Index: 628

Text #10

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.6028. Min Act: -0.1700

Data Index: 6948985 (Open Web Text)

Max Activating Token Index: 950

Text #11

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.5572. Min Act: -0.1700

Data Index: 1026159 (Open Web Text)

Max Activating Token Index: 1016

Text #12

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.5620. Min Act: -0.1700

Data Index: 3513640 (Open Web Text)

Max Activating Token Index: 1008

Text #13

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.5400. Min Act: -0.1700

Data Index: 6234755 (Open Web Text)

Max Activating Token Index: 974

Text #14

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.5631. Min Act: -0.1700

Data Index: 2354258 (Open Web Text)

Max Activating Token Index: 806

Text #15

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.5505. Min Act: -0.1700

Data Index: 2549448 (Open Web Text)

Max Activating Token Index: 345

Text #16

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.5348. Min Act: -0.1700

Data Index: 5676417 (Open Web Text)

Max Activating Token Index: 992

Text #17

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.5310. Min Act: -0.1700

Data Index: 5676413 (Open Web Text)

Max Activating Token Index: 975

Text #18

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.5381. Min Act: -0.1700

Data Index: 4436091 (Open Web Text)

Max Activating Token Index: 990

Text #19

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.5127. Min Act: -0.1700

Data Index: 6948981 (Open Web Text)

Max Activating Token Index: 901