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

Dataset: Open Web Text

Neuron 2611 in Layer 6

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: 5.0405. Min Range: -5.0405

Max Act: 5.0405. Min Act: -0.1700

Data Index: 2527780 (Open Web Text)

Max Activating Token Index: 982

Text #1

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.9210. Min Act: -0.1700

Data Index: 3209134 (Open Web Text)

Max Activating Token Index: 17

Text #2

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.8938. Min Act: -0.1700

Data Index: 3081056 (Open Web Text)

Max Activating Token Index: 528

Text #3

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.8923. Min Act: -0.1700

Data Index: 6778194 (Open Web Text)

Max Activating Token Index: 943

Text #4

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.8336. Min Act: -0.1700

Data Index: 6600113 (Open Web Text)

Max Activating Token Index: 765

Text #5

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.8276. Min Act: -0.1700

Data Index: 2189069 (Open Web Text)

Max Activating Token Index: 381

Text #6

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.7728. Min Act: -0.1700

Data Index: 7584535 (Open Web Text)

Max Activating Token Index: 557

Text #7

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.7086. Min Act: -0.1700

Data Index: 1844797 (Open Web Text)

Max Activating Token Index: 724

Text #8

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.6924. Min Act: -0.1700

Data Index: 1367981 (Open Web Text)

Max Activating Token Index: 689

Text #9

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.6585. Min Act: -0.1700

Data Index: 5666444 (Open Web Text)

Max Activating Token Index: 702

Text #10

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.6407. Min Act: -0.1700

Data Index: 3415500 (Open Web Text)

Max Activating Token Index: 844

Text #11

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.6372. Min Act: -0.1700

Data Index: 4750174 (Open Web Text)

Max Activating Token Index: 799

Text #12

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.6204. Min Act: -0.1700

Data Index: 3268122 (Open Web Text)

Max Activating Token Index: 413

Text #13

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.6489. Min Act: -0.1700

Data Index: 2533677 (Open Web Text)

Max Activating Token Index: 642

Text #14

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.6298. Min Act: -0.1700

Data Index: 6597588 (Open Web Text)

Max Activating Token Index: 534

Text #15

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.6085. Min Act: -0.1700

Data Index: 8509168 (Open Web Text)

Max Activating Token Index: 1020

Text #16

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.5921. Min Act: -0.1700

Data Index: 5702571 (Open Web Text)

Max Activating Token Index: 536

Text #17

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.6122. Min Act: -0.1700

Data Index: 6819814 (Open Web Text)

Max Activating Token Index: 648

Text #18

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.5861. Min Act: -0.1700

Data Index: 1998502 (Open Web Text)

Max Activating Token Index: 659

Text #19

Max Range: 5.0405. Min Range: -5.0405

Max Act: 4.5690. Min Act: -0.1700

Data Index: 4953940 (Open Web Text)

Max Activating Token Index: 455