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

Dataset: Open Web Text

Neuron 2628 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: 3.6542. Min Range: -3.6542

Max Act: 3.6542. Min Act: -0.1700

Data Index: 7068368 (Open Web Text)

Max Activating Token Index: 819

Text #1

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.6300. Min Act: -0.1700

Data Index: 1414141 (Open Web Text)

Max Activating Token Index: 317

Text #2

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.5099. Min Act: -0.1700

Data Index: 1030673 (Open Web Text)

Max Activating Token Index: 578

Text #3

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.5000. Min Act: -0.1700

Data Index: 4220834 (Open Web Text)

Max Activating Token Index: 314

Text #4

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.5350. Min Act: -0.1700

Data Index: 102712 (Open Web Text)

Max Activating Token Index: 476

Text #5

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.4580. Min Act: -0.1700

Data Index: 5484548 (Open Web Text)

Max Activating Token Index: 428

Text #6

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.4374. Min Act: -0.1700

Data Index: 6666359 (Open Web Text)

Max Activating Token Index: 955

Text #7

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.4128. Min Act: -0.1700

Data Index: 2363097 (Open Web Text)

Max Activating Token Index: 417

Text #8

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.4101. Min Act: -0.1700

Data Index: 4251706 (Open Web Text)

Max Activating Token Index: 906

Text #9

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3752. Min Act: -0.1700

Data Index: 1066584 (Open Web Text)

Max Activating Token Index: 807

Text #10

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3614. Min Act: -0.1700

Data Index: 2104641 (Open Web Text)

Max Activating Token Index: 768

Text #11

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3492. Min Act: -0.1700

Data Index: 4213098 (Open Web Text)

Max Activating Token Index: 980

Text #12

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3404. Min Act: -0.1700

Data Index: 6124286 (Open Web Text)

Max Activating Token Index: 489

Text #13

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3574. Min Act: -0.1700

Data Index: 7869615 (Open Web Text)

Max Activating Token Index: 453

Text #14

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3278. Min Act: -0.1700

Data Index: 7903314 (Open Web Text)

Max Activating Token Index: 871

Text #15

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3178. Min Act: -0.1700

Data Index: 673047 (Open Web Text)

Max Activating Token Index: 193

Text #16

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3142. Min Act: -0.1700

Data Index: 6094688 (Open Web Text)

Max Activating Token Index: 874

Text #17

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3087. Min Act: -0.1700

Data Index: 3525094 (Open Web Text)

Max Activating Token Index: 710

Text #18

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3043. Min Act: -0.1700

Data Index: 7216429 (Open Web Text)

Max Activating Token Index: 977

Text #19

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.2896. Min Act: -0.1700

Data Index: 2564822 (Open Web Text)

Max Activating Token Index: 359