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

Dataset: Open Web Text

Neuron 2435 in Layer 3

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: 3.8508. Min Range: -3.8508

Max Act: 3.7878. Min Act: -0.1700

Data Index: 5094686 (Open Web Text)

Max Activating Token Index: 618

Text #1

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.8508. Min Act: -0.1700

Data Index: 7936730 (Open Web Text)

Max Activating Token Index: 609

Text #2

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7860. Min Act: -0.1700

Data Index: 7734388 (Open Web Text)

Max Activating Token Index: 148

Text #3

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7444. Min Act: -0.1700

Data Index: 2539913 (Open Web Text)

Max Activating Token Index: 690

Text #4

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7208. Min Act: -0.1700

Data Index: 3715135 (Open Web Text)

Max Activating Token Index: 814

Text #5

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7324. Min Act: -0.1700

Data Index: 1231409 (Open Web Text)

Max Activating Token Index: 44

Text #6

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.6941. Min Act: -0.1700

Data Index: 453471 (Open Web Text)

Max Activating Token Index: 918

Text #7

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7266. Min Act: -0.1700

Data Index: 3147519 (Open Web Text)

Max Activating Token Index: 39

Text #8

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7670. Min Act: -0.1700

Data Index: 156968 (Open Web Text)

Max Activating Token Index: 38

Text #9

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7265. Min Act: -0.1700

Data Index: 2801454 (Open Web Text)

Max Activating Token Index: 822

Text #10

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7189. Min Act: -0.1700

Data Index: 7243116 (Open Web Text)

Max Activating Token Index: 979

Text #11

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7368. Min Act: -0.1700

Data Index: 7178845 (Open Web Text)

Max Activating Token Index: 940

Text #12

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7620. Min Act: -0.1700

Data Index: 5890063 (Open Web Text)

Max Activating Token Index: 924

Text #13

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7511. Min Act: -0.1700

Data Index: 2011371 (Open Web Text)

Max Activating Token Index: 645

Text #14

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7066. Min Act: -0.1700

Data Index: 4465993 (Open Web Text)

Max Activating Token Index: 29

Text #15

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7233. Min Act: -0.1700

Data Index: 3819872 (Open Web Text)

Max Activating Token Index: 551

Text #16

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.6875. Min Act: -0.1700

Data Index: 1070118 (Open Web Text)

Max Activating Token Index: 867

Text #17

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.6862. Min Act: -0.1700

Data Index: 3031055 (Open Web Text)

Max Activating Token Index: 1015

Text #18

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.7036. Min Act: -0.1700

Data Index: 3081107 (Open Web Text)

Max Activating Token Index: 790

Text #19

Max Range: 3.8508. Min Range: -3.8508

Max Act: 3.6503. Min Act: -0.1700

Data Index: 3693618 (Open Web Text)

Max Activating Token Index: 647