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

Dataset: Open Web Text

Neuron 1979 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: 3.8476. Min Range: -3.8476

Max Act: 3.8476. Min Act: -0.1700

Data Index: 3313735 (Open Web Text)

Max Activating Token Index: 600

Text #1

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.7033. Min Act: -0.1700

Data Index: 1402882 (Open Web Text)

Max Activating Token Index: 755

Text #2

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.6776. Min Act: -0.1700

Data Index: 3538753 (Open Web Text)

Max Activating Token Index: 503

Text #3

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.6434. Min Act: -0.1700

Data Index: 7953033 (Open Web Text)

Max Activating Token Index: 961

Text #4

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.6259. Min Act: -0.1700

Data Index: 7187637 (Open Web Text)

Max Activating Token Index: 852

Text #5

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.5946. Min Act: -0.1700

Data Index: 7096172 (Open Web Text)

Max Activating Token Index: 812

Text #6

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.5764. Min Act: -0.1700

Data Index: 5591678 (Open Web Text)

Max Activating Token Index: 664

Text #7

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.5871. Min Act: -0.1700

Data Index: 3814431 (Open Web Text)

Max Activating Token Index: 726

Text #8

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.5406. Min Act: -0.1700

Data Index: 6544029 (Open Web Text)

Max Activating Token Index: 866

Text #9

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.5527. Min Act: -0.1700

Data Index: 3611410 (Open Web Text)

Max Activating Token Index: 970

Text #10

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.5448. Min Act: -0.1700

Data Index: 5315208 (Open Web Text)

Max Activating Token Index: 993

Text #11

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.5570. Min Act: -0.1700

Data Index: 1318382 (Open Web Text)

Max Activating Token Index: 394

Text #12

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.5280. Min Act: -0.1700

Data Index: 1158686 (Open Web Text)

Max Activating Token Index: 271

Text #13

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.5171. Min Act: -0.1700

Data Index: 52903 (Open Web Text)

Max Activating Token Index: 47

Text #14

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.5150. Min Act: -0.1700

Data Index: 7095299 (Open Web Text)

Max Activating Token Index: 824

Text #15

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.4724. Min Act: -0.1700

Data Index: 6558971 (Open Web Text)

Max Activating Token Index: 837

Text #16

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.4846. Min Act: -0.1700

Data Index: 5476255 (Open Web Text)

Max Activating Token Index: 582

Text #17

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.4903. Min Act: -0.1700

Data Index: 5116175 (Open Web Text)

Max Activating Token Index: 604

Text #18

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.5066. Min Act: -0.1700

Data Index: 816176 (Open Web Text)

Max Activating Token Index: 579

Text #19

Max Range: 3.8476. Min Range: -3.8476

Max Act: 3.4777. Min Act: -0.1700

Data Index: 6755489 (Open Web Text)

Max Activating Token Index: 864