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

Dataset: Open Web Text

Neuron 382 in Layer 2

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: 1.6873. Min Range: -1.6873

Max Act: 1.6873. Min Act: -0.1700

Data Index: 6624615 (Open Web Text)

Max Activating Token Index: 477

Text #1

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6733. Min Act: -0.1700

Data Index: 4556204 (Open Web Text)

Max Activating Token Index: 430

Text #2

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6626. Min Act: -0.1700

Data Index: 3031184 (Open Web Text)

Max Activating Token Index: 331

Text #3

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6587. Min Act: -0.1700

Data Index: 6200226 (Open Web Text)

Max Activating Token Index: 368

Text #4

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6446. Min Act: -0.1700

Data Index: 942047 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6384. Min Act: -0.1700

Data Index: 320106 (Open Web Text)

Max Activating Token Index: 709

Text #6

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6368. Min Act: -0.1700

Data Index: 5703314 (Open Web Text)

Max Activating Token Index: 787

Text #7

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6302. Min Act: -0.1700

Data Index: 568416 (Open Web Text)

Max Activating Token Index: 210

Text #8

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6251. Min Act: -0.1700

Data Index: 1933342 (Open Web Text)

Max Activating Token Index: 138

Text #9

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6345. Min Act: -0.1700

Data Index: 5582333 (Open Web Text)

Max Activating Token Index: 321

Text #10

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6198. Min Act: -0.1700

Data Index: 5411511 (Open Web Text)

Max Activating Token Index: 236

Text #11

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6142. Min Act: -0.1700

Data Index: 83832 (Open Web Text)

Max Activating Token Index: 513

Text #12

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6097. Min Act: -0.1700

Data Index: 6754014 (Open Web Text)

Max Activating Token Index: 465

Text #13

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6157. Min Act: -0.1700

Data Index: 4295473 (Open Web Text)

Max Activating Token Index: 202

Text #14

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6087. Min Act: -0.1700

Data Index: 4313744 (Open Web Text)

Max Activating Token Index: 486

Text #15

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.5960. Min Act: -0.1700

Data Index: 676803 (Open Web Text)

Max Activating Token Index: 564

Text #16

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6012. Min Act: -0.1700

Data Index: 6449756 (Open Web Text)

Max Activating Token Index: 844

Text #17

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.6064. Min Act: -0.1700

Data Index: 4938850 (Open Web Text)

Max Activating Token Index: 835

Text #18

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.5978. Min Act: -0.1700

Data Index: 8094320 (Open Web Text)

Max Activating Token Index: 295

Text #19

Max Range: 1.6873. Min Range: -1.6873

Max Act: 1.5918. Min Act: -0.1700

Data Index: 3034401 (Open Web Text)

Max Activating Token Index: 727