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

Dataset: Open Web Text

Neuron 1903 in Layer 1

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: 1.0150. Min Range: -1.0150

Max Act: 1.0150. Min Act: -0.1700

Data Index: 8315101 (Open Web Text)

Max Activating Token Index: 539

Text #1

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.8385. Min Act: -0.1700

Data Index: 8131645 (Open Web Text)

Max Activating Token Index: 611

Text #2

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5598. Min Act: -0.1700

Data Index: 1610857 (Open Web Text)

Max Activating Token Index: 577

Text #3

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5469. Min Act: -0.1700

Data Index: 5028479 (Open Web Text)

Max Activating Token Index: 503

Text #4

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5526. Min Act: -0.1700

Data Index: 6934005 (Open Web Text)

Max Activating Token Index: 598

Text #5

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5272. Min Act: -0.1700

Data Index: 401356 (Open Web Text)

Max Activating Token Index: 581

Text #6

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5380. Min Act: -0.1700

Data Index: 6502183 (Open Web Text)

Max Activating Token Index: 601

Text #7

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.4717. Min Act: -0.1700

Data Index: 7084857 (Open Web Text)

Max Activating Token Index: 559

Text #8

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.4503. Min Act: -0.1700

Data Index: 7455999 (Open Web Text)

Max Activating Token Index: 668

Text #9

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.4471. Min Act: -0.1700

Data Index: 2161698 (Open Web Text)

Max Activating Token Index: 617

Text #10

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.4474. Min Act: -0.1700

Data Index: 3979451 (Open Web Text)

Max Activating Token Index: 618

Text #11

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.4118. Min Act: -0.1700

Data Index: 6575765 (Open Web Text)

Max Activating Token Index: 621

Text #12

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.4063. Min Act: -0.1700

Data Index: 6019144 (Open Web Text)

Max Activating Token Index: 628

Text #13

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.4000. Min Act: -0.1700

Data Index: 8323843 (Open Web Text)

Max Activating Token Index: 559

Text #14

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.3952. Min Act: -0.1700

Data Index: 4658327 (Open Web Text)

Max Activating Token Index: 496

Text #15

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.3748. Min Act: -0.1700

Data Index: 8542424 (Open Web Text)

Max Activating Token Index: 620

Text #16

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.3664. Min Act: -0.1700

Data Index: 8640381 (Open Web Text)

Max Activating Token Index: 524

Text #17

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.3481. Min Act: -0.1700

Data Index: 7078290 (Open Web Text)

Max Activating Token Index: 558

Text #18

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.3735. Min Act: -0.1700

Data Index: 3581592 (Open Web Text)

Max Activating Token Index: 643

Text #19

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.3520. Min Act: -0.1700

Data Index: 1044570 (Open Web Text)

Max Activating Token Index: 624