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

Dataset: Open Web Text

Neuron 2269 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: 4.6449. Min Range: -4.6449

Max Act: 4.6449. Min Act: -0.1700

Data Index: 786300 (Open Web Text)

Max Activating Token Index: 70

Text #1

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.5484. Min Act: -0.1700

Data Index: 2073841 (Open Web Text)

Max Activating Token Index: 544

Text #2

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.4969. Min Act: -0.1700

Data Index: 4545693 (Open Web Text)

Max Activating Token Index: 459

Text #3

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.4740. Min Act: -0.1700

Data Index: 7628698 (Open Web Text)

Max Activating Token Index: 193

Text #4

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.4535. Min Act: -0.1700

Data Index: 3675455 (Open Web Text)

Max Activating Token Index: 1016

Text #5

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.4625. Min Act: -0.1700

Data Index: 8418975 (Open Web Text)

Max Activating Token Index: 940

Text #6

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.4215. Min Act: -0.1700

Data Index: 3774932 (Open Web Text)

Max Activating Token Index: 464

Text #7

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.3986. Min Act: -0.1700

Data Index: 5653130 (Open Web Text)

Max Activating Token Index: 122

Text #8

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.4203. Min Act: -0.1700

Data Index: 1193571 (Open Web Text)

Max Activating Token Index: 948

Text #9

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.4083. Min Act: -0.1700

Data Index: 5100420 (Open Web Text)

Max Activating Token Index: 479

Text #10

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.4070. Min Act: -0.1700

Data Index: 2014772 (Open Web Text)

Max Activating Token Index: 433

Text #11

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.4136. Min Act: -0.1700

Data Index: 4686058 (Open Web Text)

Max Activating Token Index: 613

Text #12

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.3622. Min Act: -0.1700

Data Index: 6530513 (Open Web Text)

Max Activating Token Index: 837

Text #13

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.3796. Min Act: -0.1700

Data Index: 4771968 (Open Web Text)

Max Activating Token Index: 547

Text #14

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.4101. Min Act: -0.1700

Data Index: 7677701 (Open Web Text)

Max Activating Token Index: 420

Text #15

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.4026. Min Act: -0.1700

Data Index: 6607728 (Open Web Text)

Max Activating Token Index: 835

Text #16

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.3889. Min Act: -0.1700

Data Index: 5106187 (Open Web Text)

Max Activating Token Index: 534

Text #17

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.3919. Min Act: -0.1700

Data Index: 7941438 (Open Web Text)

Max Activating Token Index: 966

Text #18

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.3778. Min Act: -0.1700

Data Index: 7619158 (Open Web Text)

Max Activating Token Index: 699

Text #19

Max Range: 4.6449. Min Range: -4.6449

Max Act: 4.3990. Min Act: -0.1700

Data Index: 352552 (Open Web Text)

Max Activating Token Index: 786