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

Dataset: Open Web Text

Neuron 2315 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: 6.6553. Min Range: -6.6553

Max Act: 6.6553. Min Act: -0.1700

Data Index: 5393145 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.2838. Min Act: -0.1700

Data Index: 8031771 (Open Web Text)

Max Activating Token Index: 810

Text #2

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.2923. Min Act: -0.1700

Data Index: 1771708 (Open Web Text)

Max Activating Token Index: 834

Text #3

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.2396. Min Act: -0.1700

Data Index: 8713529 (Open Web Text)

Max Activating Token Index: 649

Text #4

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.2046. Min Act: -0.1700

Data Index: 3691382 (Open Web Text)

Max Activating Token Index: 797

Text #5

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.1386. Min Act: -0.1700

Data Index: 7344591 (Open Web Text)

Max Activating Token Index: 897

Text #6

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.1654. Min Act: -0.1700

Data Index: 293841 (Open Web Text)

Max Activating Token Index: 244

Text #7

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.1110. Min Act: -0.1700

Data Index: 3796912 (Open Web Text)

Max Activating Token Index: 925

Text #8

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.1566. Min Act: -0.1700

Data Index: 1779208 (Open Web Text)

Max Activating Token Index: 334

Text #9

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.1349. Min Act: -0.1700

Data Index: 653079 (Open Web Text)

Max Activating Token Index: 388

Text #10

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.1139. Min Act: -0.1700

Data Index: 2811198 (Open Web Text)

Max Activating Token Index: 895

Text #11

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.0660. Min Act: -0.1700

Data Index: 7297717 (Open Web Text)

Max Activating Token Index: 507

Text #12

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.0454. Min Act: -0.1700

Data Index: 4771212 (Open Web Text)

Max Activating Token Index: 93

Text #13

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.0668. Min Act: -0.1700

Data Index: 362661 (Open Web Text)

Max Activating Token Index: 729

Text #14

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.0071. Min Act: -0.1700

Data Index: 3402593 (Open Web Text)

Max Activating Token Index: 979

Text #15

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.0637. Min Act: -0.1700

Data Index: 4528824 (Open Web Text)

Max Activating Token Index: 949

Text #16

Max Range: 6.6553. Min Range: -6.6553

Max Act: 5.9950. Min Act: -0.1700

Data Index: 4747206 (Open Web Text)

Max Activating Token Index: 656

Text #17

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.0357. Min Act: -0.1700

Data Index: 3437637 (Open Web Text)

Max Activating Token Index: 158

Text #18

Max Range: 6.6553. Min Range: -6.6553

Max Act: 6.0113. Min Act: -0.1700

Data Index: 2163836 (Open Web Text)

Max Activating Token Index: 149

Text #19

Max Range: 6.6553. Min Range: -6.6553

Max Act: 5.9690. Min Act: -0.1700

Data Index: 6053286 (Open Web Text)

Max Activating Token Index: 656