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

Dataset: Open Web Text

Neuron 1507 in Layer 1

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: 3.8187. Min Range: -3.8187

Max Act: 3.8187. Min Act: -0.1700

Data Index: 5327622 (Open Web Text)

Max Activating Token Index: 221

Text #1

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6885. Min Act: -0.1700

Data Index: 6605521 (Open Web Text)

Max Activating Token Index: 995

Text #2

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6953. Min Act: -0.1700

Data Index: 2196961 (Open Web Text)

Max Activating Token Index: 508

Text #3

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6907. Min Act: -0.1700

Data Index: 7205471 (Open Web Text)

Max Activating Token Index: 64

Text #4

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6591. Min Act: -0.1700

Data Index: 4269954 (Open Web Text)

Max Activating Token Index: 1010

Text #5

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6911. Min Act: -0.1700

Data Index: 4876286 (Open Web Text)

Max Activating Token Index: 743

Text #6

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6365. Min Act: -0.1700

Data Index: 3844098 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6550. Min Act: -0.1700

Data Index: 7030883 (Open Web Text)

Max Activating Token Index: 1015

Text #8

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6315. Min Act: -0.1700

Data Index: 4283025 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6475. Min Act: -0.1700

Data Index: 7874712 (Open Web Text)

Max Activating Token Index: 759

Text #10

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6326. Min Act: -0.1700

Data Index: 6473856 (Open Web Text)

Max Activating Token Index: 28

Text #11

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6539. Min Act: -0.1700

Data Index: 2253311 (Open Web Text)

Max Activating Token Index: 69

Text #12

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6289. Min Act: -0.1700

Data Index: 757367 (Open Web Text)

Max Activating Token Index: 1021

Text #13

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6156. Min Act: -0.1700

Data Index: 6307589 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6002. Min Act: -0.1700

Data Index: 6124009 (Open Web Text)

Max Activating Token Index: 984

Text #15

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6258. Min Act: -0.1700

Data Index: 6095848 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6138. Min Act: -0.1700

Data Index: 5817734 (Open Web Text)

Max Activating Token Index: 621

Text #17

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6341. Min Act: -0.1700

Data Index: 5527292 (Open Web Text)

Max Activating Token Index: 478

Text #18

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6247. Min Act: -0.1700

Data Index: 729970 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6007. Min Act: -0.1700

Data Index: 1809021 (Open Web Text)

Max Activating Token Index: 626