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

Dataset: Open Web Text

Neuron 2269 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: 4.5418. Min Range: -4.5418

Max Act: 4.5418. Min Act: -0.1700

Data Index: 7432283 (Open Web Text)

Max Activating Token Index: 921

Text #1

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.4799. Min Act: -0.1700

Data Index: 1238571 (Open Web Text)

Max Activating Token Index: 556

Text #2

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.5178. Min Act: -0.1700

Data Index: 772051 (Open Web Text)

Max Activating Token Index: 1020

Text #3

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.4654. Min Act: -0.1700

Data Index: 8132242 (Open Web Text)

Max Activating Token Index: 158

Text #4

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.4664. Min Act: -0.1700

Data Index: 7510952 (Open Web Text)

Max Activating Token Index: 879

Text #5

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.4406. Min Act: -0.1700

Data Index: 6914397 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3891. Min Act: -0.1700

Data Index: 7022340 (Open Web Text)

Max Activating Token Index: 799

Text #7

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3978. Min Act: -0.1700

Data Index: 1917819 (Open Web Text)

Max Activating Token Index: 847

Text #8

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3897. Min Act: -0.1700

Data Index: 6732094 (Open Web Text)

Max Activating Token Index: 744

Text #9

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3988. Min Act: -0.1700

Data Index: 3248343 (Open Web Text)

Max Activating Token Index: 194

Text #10

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3796. Min Act: -0.1700

Data Index: 458045 (Open Web Text)

Max Activating Token Index: 484

Text #11

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3880. Min Act: -0.1700

Data Index: 297968 (Open Web Text)

Max Activating Token Index: 610

Text #12

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3776. Min Act: -0.1700

Data Index: 970265 (Open Web Text)

Max Activating Token Index: 550

Text #13

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3566. Min Act: -0.1700

Data Index: 7298529 (Open Web Text)

Max Activating Token Index: 565

Text #14

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3585. Min Act: -0.1700

Data Index: 6440123 (Open Web Text)

Max Activating Token Index: 355

Text #15

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3759. Min Act: -0.1700

Data Index: 8187881 (Open Web Text)

Max Activating Token Index: 704

Text #16

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3442. Min Act: -0.1700

Data Index: 2832738 (Open Web Text)

Max Activating Token Index: 559

Text #17

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3400. Min Act: -0.1700

Data Index: 7623900 (Open Web Text)

Max Activating Token Index: 734

Text #18

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3276. Min Act: -0.1700

Data Index: 3428917 (Open Web Text)

Max Activating Token Index: 508

Text #19

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.3228. Min Act: -0.1700

Data Index: 3146856 (Open Web Text)

Max Activating Token Index: 221