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

Dataset: Open Web Text

Neuron 342 in Layer 3

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: 3.7998. Min Range: -3.7998

Max Act: 3.7998. Min Act: -0.1700

Data Index: 6755877 (Open Web Text)

Max Activating Token Index: 413

Text #1

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.7379. Min Act: -0.1700

Data Index: 1923394 (Open Web Text)

Max Activating Token Index: 552

Text #2

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.7310. Min Act: -0.1700

Data Index: 3709517 (Open Web Text)

Max Activating Token Index: 611

Text #3

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.7513. Min Act: -0.1700

Data Index: 3610239 (Open Web Text)

Max Activating Token Index: 331

Text #4

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.7368. Min Act: -0.1700

Data Index: 7649328 (Open Web Text)

Max Activating Token Index: 335

Text #5

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.6771. Min Act: -0.1700

Data Index: 6252071 (Open Web Text)

Max Activating Token Index: 498

Text #6

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.7134. Min Act: -0.1700

Data Index: 3985848 (Open Web Text)

Max Activating Token Index: 669

Text #7

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.7069. Min Act: -0.1700

Data Index: 5528706 (Open Web Text)

Max Activating Token Index: 827

Text #8

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.7102. Min Act: -0.1700

Data Index: 2625424 (Open Web Text)

Max Activating Token Index: 322

Text #9

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.7066. Min Act: -0.1700

Data Index: 8533083 (Open Web Text)

Max Activating Token Index: 645

Text #10

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.6872. Min Act: -0.1700

Data Index: 7239451 (Open Web Text)

Max Activating Token Index: 767

Text #11

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.6730. Min Act: -0.1700

Data Index: 7478914 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.6874. Min Act: -0.1700

Data Index: 6735114 (Open Web Text)

Max Activating Token Index: 452

Text #13

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.6528. Min Act: -0.1700

Data Index: 4858284 (Open Web Text)

Max Activating Token Index: 264

Text #14

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.6493. Min Act: -0.1700

Data Index: 1827031 (Open Web Text)

Max Activating Token Index: 892

Text #15

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.6376. Min Act: -0.1700

Data Index: 2684428 (Open Web Text)

Max Activating Token Index: 854

Text #16

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.6581. Min Act: -0.1700

Data Index: 3973627 (Open Web Text)

Max Activating Token Index: 830

Text #17

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.6539. Min Act: -0.1700

Data Index: 8188823 (Open Web Text)

Max Activating Token Index: 405

Text #18

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.6633. Min Act: -0.1700

Data Index: 1079580 (Open Web Text)

Max Activating Token Index: 488

Text #19

Max Range: 3.7998. Min Range: -3.7998

Max Act: 3.6358. Min Act: -0.1700

Data Index: 2285933 (Open Web Text)

Max Activating Token Index: 31