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

Dataset: Open Web Text

Neuron 499 in Layer 2

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: 3.8877. Min Range: -3.8877

Max Act: 3.8877. Min Act: -0.1700

Data Index: 5292924 (Open Web Text)

Max Activating Token Index: 455

Text #1

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.8641. Min Act: -0.1700

Data Index: 7826074 (Open Web Text)

Max Activating Token Index: 350

Text #2

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7566. Min Act: -0.1700

Data Index: 5881741 (Open Web Text)

Max Activating Token Index: 963

Text #3

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7490. Min Act: -0.1700

Data Index: 584541 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7558. Min Act: -0.1700

Data Index: 5582992 (Open Web Text)

Max Activating Token Index: 560

Text #5

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7240. Min Act: -0.1700

Data Index: 5563624 (Open Web Text)

Max Activating Token Index: 994

Text #6

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7378. Min Act: -0.1700

Data Index: 7182064 (Open Web Text)

Max Activating Token Index: 196

Text #7

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7262. Min Act: -0.1700

Data Index: 7914082 (Open Web Text)

Max Activating Token Index: 786

Text #8

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7244. Min Act: -0.1700

Data Index: 3822534 (Open Web Text)

Max Activating Token Index: 614

Text #9

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7380. Min Act: -0.1700

Data Index: 3253071 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7454. Min Act: -0.1700

Data Index: 4616160 (Open Web Text)

Max Activating Token Index: 323

Text #11

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7495. Min Act: -0.1700

Data Index: 6537341 (Open Web Text)

Max Activating Token Index: 604

Text #12

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.6974. Min Act: -0.1700

Data Index: 1332521 (Open Web Text)

Max Activating Token Index: 416

Text #13

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.6887. Min Act: -0.1700

Data Index: 7940849 (Open Web Text)

Max Activating Token Index: 529

Text #14

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7056. Min Act: -0.1700

Data Index: 7564474 (Open Web Text)

Max Activating Token Index: 574

Text #15

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7145. Min Act: -0.1700

Data Index: 4276114 (Open Web Text)

Max Activating Token Index: 330

Text #16

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7118. Min Act: -0.1700

Data Index: 1115789 (Open Web Text)

Max Activating Token Index: 911

Text #17

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.6757. Min Act: -0.1700

Data Index: 7758984 (Open Web Text)

Max Activating Token Index: 524

Text #18

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.6913. Min Act: -0.1700

Data Index: 4519659 (Open Web Text)

Max Activating Token Index: 520

Text #19

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.6598. Min Act: -0.1700

Data Index: 332834 (Open Web Text)

Max Activating Token Index: 165