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

Dataset: Open Web Text

Neuron 385 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: 4.7018. Min Range: -4.7018

Max Act: 4.7018. Min Act: -0.1700

Data Index: 2491572 (Open Web Text)

Max Activating Token Index: 784

Text #1

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.6588. Min Act: -0.1700

Data Index: 739204 (Open Web Text)

Max Activating Token Index: 365

Text #2

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.5580. Min Act: -0.1700

Data Index: 3237965 (Open Web Text)

Max Activating Token Index: 391

Text #3

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.4898. Min Act: -0.1700

Data Index: 7509423 (Open Web Text)

Max Activating Token Index: 84

Text #4

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.4155. Min Act: -0.1700

Data Index: 7233441 (Open Web Text)

Max Activating Token Index: 399

Text #5

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.4478. Min Act: -0.1700

Data Index: 2533565 (Open Web Text)

Max Activating Token Index: 550

Text #6

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.4263. Min Act: -0.1700

Data Index: 1224668 (Open Web Text)

Max Activating Token Index: 632

Text #7

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.4268. Min Act: -0.1700

Data Index: 3034522 (Open Web Text)

Max Activating Token Index: 284

Text #8

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.3934. Min Act: -0.1700

Data Index: 3038695 (Open Web Text)

Max Activating Token Index: 641

Text #9

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.3766. Min Act: -0.1700

Data Index: 7758281 (Open Web Text)

Max Activating Token Index: 756

Text #10

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.3872. Min Act: -0.1700

Data Index: 7099215 (Open Web Text)

Max Activating Token Index: 233

Text #11

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.3554. Min Act: -0.1700

Data Index: 5371141 (Open Web Text)

Max Activating Token Index: 292

Text #12

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.3185. Min Act: -0.1700

Data Index: 4326822 (Open Web Text)

Max Activating Token Index: 39

Text #13

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.2969. Min Act: -0.1700

Data Index: 6108456 (Open Web Text)

Max Activating Token Index: 697

Text #14

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.3134. Min Act: -0.1700

Data Index: 631757 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.2714. Min Act: -0.1700

Data Index: 8115981 (Open Web Text)

Max Activating Token Index: 305

Text #16

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.3017. Min Act: -0.1700

Data Index: 6799379 (Open Web Text)

Max Activating Token Index: 910

Text #17

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.3085. Min Act: -0.1700

Data Index: 7122173 (Open Web Text)

Max Activating Token Index: 791

Text #18

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.2997. Min Act: -0.1700

Data Index: 5379694 (Open Web Text)

Max Activating Token Index: 718

Text #19

Max Range: 4.7018. Min Range: -4.7018

Max Act: 4.3128. Min Act: -0.1700

Data Index: 7665763 (Open Web Text)

Max Activating Token Index: 321