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

Dataset: Open Web Text

Neuron 2286 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: 6.2131. Min Range: -6.2131

Max Act: 6.2131. Min Act: -0.1700

Data Index: 2432948 (Open Web Text)

Max Activating Token Index: 779

Text #1

Max Range: 6.2131. Min Range: -6.2131

Max Act: 6.0538. Min Act: -0.1700

Data Index: 5119803 (Open Web Text)

Max Activating Token Index: 490

Text #2

Max Range: 6.2131. Min Range: -6.2131

Max Act: 6.0204. Min Act: -0.1700

Data Index: 1943105 (Open Web Text)

Max Activating Token Index: 918

Text #3

Max Range: 6.2131. Min Range: -6.2131

Max Act: 6.0458. Min Act: -0.1700

Data Index: 4324699 (Open Web Text)

Max Activating Token Index: 702

Text #4

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.9593. Min Act: -0.1700

Data Index: 2507676 (Open Web Text)

Max Activating Token Index: 598

Text #5

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.9720. Min Act: -0.1700

Data Index: 489476 (Open Web Text)

Max Activating Token Index: 929

Text #6

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.8508. Min Act: -0.1700

Data Index: 207079 (Open Web Text)

Max Activating Token Index: 854

Text #7

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.8880. Min Act: -0.1700

Data Index: 256151 (Open Web Text)

Max Activating Token Index: 932

Text #8

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.8675. Min Act: -0.1700

Data Index: 2605066 (Open Web Text)

Max Activating Token Index: 761

Text #9

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.8088. Min Act: -0.1700

Data Index: 3896345 (Open Web Text)

Max Activating Token Index: 940

Text #10

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.8213. Min Act: -0.1700

Data Index: 6376508 (Open Web Text)

Max Activating Token Index: 407

Text #11

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.8288. Min Act: -0.1700

Data Index: 4253800 (Open Web Text)

Max Activating Token Index: 466

Text #12

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.8215. Min Act: -0.1700

Data Index: 6064246 (Open Web Text)

Max Activating Token Index: 484

Text #13

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.8366. Min Act: -0.1700

Data Index: 8745177 (Open Web Text)

Max Activating Token Index: 410

Text #14

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.7921. Min Act: -0.1700

Data Index: 6732134 (Open Web Text)

Max Activating Token Index: 747

Text #15

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.7919. Min Act: -0.1700

Data Index: 5458967 (Open Web Text)

Max Activating Token Index: 570

Text #16

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.7767. Min Act: -0.1700

Data Index: 4554178 (Open Web Text)

Max Activating Token Index: 571

Text #17

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.7737. Min Act: -0.1700

Data Index: 2980587 (Open Web Text)

Max Activating Token Index: 675

Text #18

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.7905. Min Act: -0.1700

Data Index: 6132523 (Open Web Text)

Max Activating Token Index: 618

Text #19

Max Range: 6.2131. Min Range: -6.2131

Max Act: 5.7496. Min Act: -0.1700

Data Index: 204156 (Open Web Text)

Max Activating Token Index: 160