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

Dataset: Open Web Text

Neuron 2049 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: 1.8569. Min Range: -1.8569

Max Act: 1.8569. Min Act: -0.1700

Data Index: 2582258 (Open Web Text)

Max Activating Token Index: 679

Text #1

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7798. Min Act: -0.1700

Data Index: 4698665 (Open Web Text)

Max Activating Token Index: 173

Text #2

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7778. Min Act: -0.1700

Data Index: 1967360 (Open Web Text)

Max Activating Token Index: 320

Text #3

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7781. Min Act: -0.1700

Data Index: 4155912 (Open Web Text)

Max Activating Token Index: 281

Text #4

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7695. Min Act: -0.1700

Data Index: 1000996 (Open Web Text)

Max Activating Token Index: 910

Text #5

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7585. Min Act: -0.1700

Data Index: 1009194 (Open Web Text)

Max Activating Token Index: 233

Text #6

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7532. Min Act: -0.1700

Data Index: 6487508 (Open Web Text)

Max Activating Token Index: 160

Text #7

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7598. Min Act: -0.1700

Data Index: 5850674 (Open Web Text)

Max Activating Token Index: 265

Text #8

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7594. Min Act: -0.1683

Data Index: 5586945 (Open Web Text)

Max Activating Token Index: 639

Text #9

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7569. Min Act: -0.1700

Data Index: 7689512 (Open Web Text)

Max Activating Token Index: 587

Text #10

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7613. Min Act: -0.1700

Data Index: 5152298 (Open Web Text)

Max Activating Token Index: 88

Text #11

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7527. Min Act: -0.1700

Data Index: 1662403 (Open Web Text)

Max Activating Token Index: 389

Text #12

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7547. Min Act: -0.1700

Data Index: 7978465 (Open Web Text)

Max Activating Token Index: 453

Text #13

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7399. Min Act: -0.1700

Data Index: 2494514 (Open Web Text)

Max Activating Token Index: 451

Text #14

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7442. Min Act: -0.1700

Data Index: 8678654 (Open Web Text)

Max Activating Token Index: 534

Text #15

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7436. Min Act: -0.1698

Data Index: 6998802 (Open Web Text)

Max Activating Token Index: 719

Text #16

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7445. Min Act: -0.1700

Data Index: 1442082 (Open Web Text)

Max Activating Token Index: 458

Text #17

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7353. Min Act: -0.1700

Data Index: 6286648 (Open Web Text)

Max Activating Token Index: 696

Text #18

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7343. Min Act: -0.1700

Data Index: 3622843 (Open Web Text)

Max Activating Token Index: 436

Text #19

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7386. Min Act: -0.1700

Data Index: 5028066 (Open Web Text)

Max Activating Token Index: 557