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

Dataset: Open Web Text

Neuron 389 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: 3.0510. Min Range: -3.0510

Max Act: 3.0510. Min Act: -0.1700

Data Index: 5156135 (Open Web Text)

Max Activating Token Index: 505

Text #1

Max Range: 3.0510. Min Range: -3.0510

Max Act: 3.0359. Min Act: -0.1700

Data Index: 4751429 (Open Web Text)

Max Activating Token Index: 528

Text #2

Max Range: 3.0510. Min Range: -3.0510

Max Act: 3.0237. Min Act: -0.1700

Data Index: 6148176 (Open Web Text)

Max Activating Token Index: 495

Text #3

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9920. Min Act: -0.1700

Data Index: 3523 (Open Web Text)

Max Activating Token Index: 416

Text #4

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9526. Min Act: -0.1700

Data Index: 5984018 (Open Web Text)

Max Activating Token Index: 512

Text #5

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9616. Min Act: -0.1700

Data Index: 3882258 (Open Web Text)

Max Activating Token Index: 753

Text #6

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9425. Min Act: -0.1700

Data Index: 8530736 (Open Web Text)

Max Activating Token Index: 24

Text #7

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9457. Min Act: -0.1700

Data Index: 6365498 (Open Web Text)

Max Activating Token Index: 720

Text #8

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9287. Min Act: -0.1700

Data Index: 7170106 (Open Web Text)

Max Activating Token Index: 341

Text #9

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8945. Min Act: -0.1700

Data Index: 7114348 (Open Web Text)

Max Activating Token Index: 314

Text #10

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9380. Min Act: -0.1700

Data Index: 8259077 (Open Web Text)

Max Activating Token Index: 51

Text #11

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9023. Min Act: -0.1700

Data Index: 6500694 (Open Web Text)

Max Activating Token Index: 707

Text #12

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9214. Min Act: -0.1700

Data Index: 8741414 (Open Web Text)

Max Activating Token Index: 323

Text #13

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9044. Min Act: -0.1700

Data Index: 8076322 (Open Web Text)

Max Activating Token Index: 654

Text #14

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8856. Min Act: -0.1700

Data Index: 7715221 (Open Web Text)

Max Activating Token Index: 768

Text #15

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8940. Min Act: -0.1700

Data Index: 3564634 (Open Web Text)

Max Activating Token Index: 335

Text #16

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.9272. Min Act: -0.1700

Data Index: 4380787 (Open Web Text)

Max Activating Token Index: 402

Text #17

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8749. Min Act: -0.1700

Data Index: 8766329 (Open Web Text)

Max Activating Token Index: 962

Text #18

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8669. Min Act: -0.1700

Data Index: 2443093 (Open Web Text)

Max Activating Token Index: 770

Text #19

Max Range: 3.0510. Min Range: -3.0510

Max Act: 2.8660. Min Act: -0.1700

Data Index: 7427575 (Open Web Text)

Max Activating Token Index: 310