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

Dataset: Open Web Text

Neuron 501 in Layer 3

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: 3.9798. Min Range: -3.9798

Max Act: 3.9798. Min Act: -0.1700

Data Index: 6257727 (Open Web Text)

Max Activating Token Index: 383

Text #1

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.9730. Min Act: -0.1700

Data Index: 2206994 (Open Web Text)

Max Activating Token Index: 866

Text #2

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.9358. Min Act: -0.1700

Data Index: 7425497 (Open Web Text)

Max Activating Token Index: 646

Text #3

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.9241. Min Act: -0.1700

Data Index: 3852670 (Open Web Text)

Max Activating Token Index: 296

Text #4

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.8651. Min Act: -0.1700

Data Index: 131234 (Open Web Text)

Max Activating Token Index: 243

Text #5

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.9062. Min Act: -0.1700

Data Index: 4335235 (Open Web Text)

Max Activating Token Index: 601

Text #6

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.8885. Min Act: -0.1700

Data Index: 4491433 (Open Web Text)

Max Activating Token Index: 159

Text #7

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.8705. Min Act: -0.1700

Data Index: 7699801 (Open Web Text)

Max Activating Token Index: 480

Text #8

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.8668. Min Act: -0.1700

Data Index: 821956 (Open Web Text)

Max Activating Token Index: 489

Text #9

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.8610. Min Act: -0.1700

Data Index: 5231789 (Open Web Text)

Max Activating Token Index: 275

Text #10

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.8569. Min Act: -0.1700

Data Index: 810039 (Open Web Text)

Max Activating Token Index: 636

Text #11

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.8336. Min Act: -0.1700

Data Index: 4563052 (Open Web Text)

Max Activating Token Index: 543

Text #12

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.8294. Min Act: -0.1700

Data Index: 8163224 (Open Web Text)

Max Activating Token Index: 333

Text #13

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.8368. Min Act: -0.1700

Data Index: 3417572 (Open Web Text)

Max Activating Token Index: 526

Text #14

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.8004. Min Act: -0.1700

Data Index: 7163004 (Open Web Text)

Max Activating Token Index: 736

Text #15

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.7850. Min Act: -0.1700

Data Index: 2943912 (Open Web Text)

Max Activating Token Index: 690

Text #16

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.7729. Min Act: -0.1700

Data Index: 3091021 (Open Web Text)

Max Activating Token Index: 609

Text #17

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.7606. Min Act: -0.1700

Data Index: 5221983 (Open Web Text)

Max Activating Token Index: 840

Text #18

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.7657. Min Act: -0.1700

Data Index: 3377119 (Open Web Text)

Max Activating Token Index: 530

Text #19

Max Range: 3.9798. Min Range: -3.9798

Max Act: 3.7954. Min Act: -0.1700

Data Index: 1066768 (Open Web Text)

Max Activating Token Index: 181