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

Dataset: Open Web Text

Neuron 149 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: 4.0741. Min Range: -4.0741

Max Act: 4.0741. Min Act: -0.1700

Data Index: 3781430 (Open Web Text)

Max Activating Token Index: 449

Text #1

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0304. Min Act: -0.1700

Data Index: 7249219 (Open Web Text)

Max Activating Token Index: 546

Text #2

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0399. Min Act: -0.1700

Data Index: 2604644 (Open Web Text)

Max Activating Token Index: 681

Text #3

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0325. Min Act: -0.1700

Data Index: 2388059 (Open Web Text)

Max Activating Token Index: 905

Text #4

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9481. Min Act: -0.1700

Data Index: 1708188 (Open Web Text)

Max Activating Token Index: 495

Text #5

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9634. Min Act: -0.1700

Data Index: 1145305 (Open Web Text)

Max Activating Token Index: 126

Text #6

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9616. Min Act: -0.1700

Data Index: 4762519 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9616. Min Act: -0.1700

Data Index: 3394162 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9525. Min Act: -0.1700

Data Index: 7284321 (Open Web Text)

Max Activating Token Index: 95

Text #9

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9496. Min Act: -0.1700

Data Index: 7476208 (Open Web Text)

Max Activating Token Index: 137

Text #10

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9733. Min Act: -0.1700

Data Index: 7768352 (Open Web Text)

Max Activating Token Index: 513

Text #11

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9438. Min Act: -0.1700

Data Index: 5266437 (Open Web Text)

Max Activating Token Index: 801

Text #12

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9329. Min Act: -0.1700

Data Index: 7950897 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9037. Min Act: -0.1700

Data Index: 3380842 (Open Web Text)

Max Activating Token Index: 663

Text #14

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9689. Min Act: -0.1700

Data Index: 7331682 (Open Web Text)

Max Activating Token Index: 575

Text #15

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9375. Min Act: -0.1700

Data Index: 792119 (Open Web Text)

Max Activating Token Index: 533

Text #16

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9222. Min Act: -0.1700

Data Index: 7086117 (Open Web Text)

Max Activating Token Index: 958

Text #17

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9480. Min Act: -0.1700

Data Index: 1255635 (Open Web Text)

Max Activating Token Index: 381

Text #18

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9493. Min Act: -0.1700

Data Index: 6937113 (Open Web Text)

Max Activating Token Index: 238

Text #19

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9470. Min Act: -0.1700

Data Index: 5567415 (Open Web Text)

Max Activating Token Index: 13