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

Dataset: Open Web Text

Neuron 2652 in Layer 4

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: 3.3253. Min Range: -3.3253

Max Act: 3.3253. Min Act: -0.1700

Data Index: 6858497 (Open Web Text)

Max Activating Token Index: 956

Text #1

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.3173. Min Act: -0.1700

Data Index: 4945169 (Open Web Text)

Max Activating Token Index: 990

Text #2

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.2763. Min Act: -0.1700

Data Index: 3294115 (Open Web Text)

Max Activating Token Index: 911

Text #3

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.2294. Min Act: -0.1700

Data Index: 7747971 (Open Web Text)

Max Activating Token Index: 890

Text #4

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.2102. Min Act: -0.1700

Data Index: 3002161 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1776. Min Act: -0.1700

Data Index: 5886440 (Open Web Text)

Max Activating Token Index: 552

Text #6

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1735. Min Act: -0.1700

Data Index: 3541502 (Open Web Text)

Max Activating Token Index: 1015

Text #7

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1876. Min Act: -0.1700

Data Index: 1283639 (Open Web Text)

Max Activating Token Index: 771

Text #8

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1532. Min Act: -0.1700

Data Index: 5201093 (Open Web Text)

Max Activating Token Index: 862

Text #9

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1693. Min Act: -0.1700

Data Index: 6739202 (Open Web Text)

Max Activating Token Index: 638

Text #10

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1823. Min Act: -0.1700

Data Index: 3002158 (Open Web Text)

Max Activating Token Index: 935

Text #11

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1772. Min Act: -0.1700

Data Index: 978760 (Open Web Text)

Max Activating Token Index: 994

Text #12

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1346. Min Act: -0.1700

Data Index: 1504099 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1694. Min Act: -0.1700

Data Index: 1134539 (Open Web Text)

Max Activating Token Index: 930

Text #14

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1366. Min Act: -0.1700

Data Index: 6370125 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1568. Min Act: -0.1700

Data Index: 339960 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1480. Min Act: -0.1700

Data Index: 4080532 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1438. Min Act: -0.1700

Data Index: 7663832 (Open Web Text)

Max Activating Token Index: 686

Text #18

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1346. Min Act: -0.1700

Data Index: 2669295 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1495. Min Act: -0.1700

Data Index: 2636736 (Open Web Text)

Max Activating Token Index: 477