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

Dataset: Open Web Text

Neuron 30 in Layer 4

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: 1.8634. Min Range: -1.8634

Max Act: 1.8634. Min Act: -0.1700

Data Index: 1431982 (Open Web Text)

Max Activating Token Index: 901

Text #1

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.8282. Min Act: -0.1700

Data Index: 5616027 (Open Web Text)

Max Activating Token Index: 213

Text #2

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.8138. Min Act: -0.1700

Data Index: 5591308 (Open Web Text)

Max Activating Token Index: 443

Text #3

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7866. Min Act: -0.1700

Data Index: 2081920 (Open Web Text)

Max Activating Token Index: 213

Text #4

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7890. Min Act: -0.1700

Data Index: 2223430 (Open Web Text)

Max Activating Token Index: 703

Text #5

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7839. Min Act: -0.1700

Data Index: 1789128 (Open Web Text)

Max Activating Token Index: 694

Text #6

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7935. Min Act: -0.1700

Data Index: 7988352 (Open Web Text)

Max Activating Token Index: 799

Text #7

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7600. Min Act: -0.1700

Data Index: 6726524 (Open Web Text)

Max Activating Token Index: 68

Text #8

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7707. Min Act: -0.1700

Data Index: 4323708 (Open Web Text)

Max Activating Token Index: 1002

Text #9

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7626. Min Act: -0.1700

Data Index: 5474367 (Open Web Text)

Max Activating Token Index: 234

Text #10

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7468. Min Act: -0.1700

Data Index: 569225 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7620. Min Act: -0.1700

Data Index: 6452376 (Open Web Text)

Max Activating Token Index: 790

Text #12

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7523. Min Act: -0.1700

Data Index: 36936 (Open Web Text)

Max Activating Token Index: 606

Text #13

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7650. Min Act: -0.1700

Data Index: 8757143 (Open Web Text)

Max Activating Token Index: 625

Text #14

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7471. Min Act: -0.1700

Data Index: 838154 (Open Web Text)

Max Activating Token Index: 976

Text #15

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7490. Min Act: -0.1700

Data Index: 5373520 (Open Web Text)

Max Activating Token Index: 610

Text #16

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7517. Min Act: -0.1700

Data Index: 4235178 (Open Web Text)

Max Activating Token Index: 309

Text #17

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7533. Min Act: -0.1700

Data Index: 991546 (Open Web Text)

Max Activating Token Index: 697

Text #18

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7451. Min Act: -0.1700

Data Index: 6287559 (Open Web Text)

Max Activating Token Index: 250

Text #19

Max Range: 1.8634. Min Range: -1.8634

Max Act: 1.7400. Min Act: -0.1700

Data Index: 762517 (Open Web Text)

Max Activating Token Index: 282