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

Dataset: Open Web Text

Neuron 320 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: 4.5733. Min Range: -4.5733

Max Act: 4.5733. Min Act: -0.1700

Data Index: 4748577 (Open Web Text)

Max Activating Token Index: 262

Text #1

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.5637. Min Act: -0.1700

Data Index: 8505229 (Open Web Text)

Max Activating Token Index: 516

Text #2

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.5088. Min Act: -0.1700

Data Index: 6073555 (Open Web Text)

Max Activating Token Index: 270

Text #3

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.5227. Min Act: -0.1700

Data Index: 4839181 (Open Web Text)

Max Activating Token Index: 996

Text #4

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.5146. Min Act: -0.1700

Data Index: 5610626 (Open Web Text)

Max Activating Token Index: 406

Text #5

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.5267. Min Act: -0.1700

Data Index: 4290160 (Open Web Text)

Max Activating Token Index: 650

Text #6

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.4960. Min Act: -0.1700

Data Index: 6392597 (Open Web Text)

Max Activating Token Index: 259

Text #7

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.4324. Min Act: -0.1700

Data Index: 1852725 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.3922. Min Act: -0.1700

Data Index: 3176535 (Open Web Text)

Max Activating Token Index: 819

Text #9

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.3893. Min Act: -0.1700

Data Index: 6693214 (Open Web Text)

Max Activating Token Index: 280

Text #10

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.3759. Min Act: -0.1700

Data Index: 1841303 (Open Web Text)

Max Activating Token Index: 498

Text #11

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.3771. Min Act: -0.1700

Data Index: 7607074 (Open Web Text)

Max Activating Token Index: 394

Text #12

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.3897. Min Act: -0.1700

Data Index: 5638697 (Open Web Text)

Max Activating Token Index: 1004

Text #13

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.3401. Min Act: -0.1700

Data Index: 4589690 (Open Web Text)

Max Activating Token Index: 865

Text #14

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.3393. Min Act: -0.1700

Data Index: 5136317 (Open Web Text)

Max Activating Token Index: 593

Text #15

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.3396. Min Act: -0.1700

Data Index: 1910830 (Open Web Text)

Max Activating Token Index: 753

Text #16

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.3240. Min Act: -0.1700

Data Index: 8823078 (Open Web Text)

Max Activating Token Index: 422

Text #17

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.3055. Min Act: -0.1700

Data Index: 6168236 (Open Web Text)

Max Activating Token Index: 616

Text #18

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.3185. Min Act: -0.1700

Data Index: 2725928 (Open Web Text)

Max Activating Token Index: 133

Text #19

Max Range: 4.5733. Min Range: -4.5733

Max Act: 4.2776. Min Act: -0.1700

Data Index: 2425375 (Open Web Text)

Max Activating Token Index: 137