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

Dataset: Open Web Text

Neuron 1938 in Layer 5

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: 3.6084. Min Range: -3.6084

Max Act: 3.6084. Min Act: -0.1700

Data Index: 5123831 (Open Web Text)

Max Activating Token Index: 1017

Text #1

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.5249. Min Act: -0.1700

Data Index: 3392283 (Open Web Text)

Max Activating Token Index: 317

Text #2

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.5069. Min Act: -0.1700

Data Index: 92504 (Open Web Text)

Max Activating Token Index: 1021

Text #3

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.5046. Min Act: -0.1700

Data Index: 2862419 (Open Web Text)

Max Activating Token Index: 335

Text #4

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4811. Min Act: -0.1700

Data Index: 6657546 (Open Web Text)

Max Activating Token Index: 988

Text #5

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4818. Min Act: -0.1700

Data Index: 345611 (Open Web Text)

Max Activating Token Index: 747

Text #6

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4997. Min Act: -0.1700

Data Index: 6097760 (Open Web Text)

Max Activating Token Index: 438

Text #7

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4907. Min Act: -0.1700

Data Index: 1373081 (Open Web Text)

Max Activating Token Index: 595

Text #8

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4801. Min Act: -0.1700

Data Index: 4207047 (Open Web Text)

Max Activating Token Index: 438

Text #9

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4569. Min Act: -0.1700

Data Index: 6189188 (Open Web Text)

Max Activating Token Index: 972

Text #10

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4521. Min Act: -0.1700

Data Index: 1498404 (Open Web Text)

Max Activating Token Index: 978

Text #11

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4451. Min Act: -0.1700

Data Index: 4834920 (Open Web Text)

Max Activating Token Index: 991

Text #12

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4480. Min Act: -0.1700

Data Index: 5017131 (Open Web Text)

Max Activating Token Index: 309

Text #13

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4607. Min Act: -0.1700

Data Index: 654947 (Open Web Text)

Max Activating Token Index: 557

Text #14

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4414. Min Act: -0.1700

Data Index: 6897616 (Open Web Text)

Max Activating Token Index: 436

Text #15

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4514. Min Act: -0.1700

Data Index: 1755153 (Open Web Text)

Max Activating Token Index: 906

Text #16

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4545. Min Act: -0.1700

Data Index: 6466403 (Open Web Text)

Max Activating Token Index: 574

Text #17

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4424. Min Act: -0.1700

Data Index: 4987850 (Open Web Text)

Max Activating Token Index: 423

Text #18

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4437. Min Act: -0.1700

Data Index: 2969814 (Open Web Text)

Max Activating Token Index: 606

Text #19

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.4508. Min Act: -0.1700

Data Index: 5512697 (Open Web Text)

Max Activating Token Index: 656