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

Dataset: Open Web Text

Neuron 3025 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: 3.5627. Min Range: -3.5627

Max Act: 3.5627. Min Act: -0.1700

Data Index: 7428832 (Open Web Text)

Max Activating Token Index: 674

Text #1

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.5449. Min Act: -0.1700

Data Index: 6648855 (Open Web Text)

Max Activating Token Index: 516

Text #2

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.5432. Min Act: -0.1700

Data Index: 3239184 (Open Web Text)

Max Activating Token Index: 954

Text #3

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.5052. Min Act: -0.1700

Data Index: 5185982 (Open Web Text)

Max Activating Token Index: 353

Text #4

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4669. Min Act: -0.1700

Data Index: 1772984 (Open Web Text)

Max Activating Token Index: 219

Text #5

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4412. Min Act: -0.1700

Data Index: 4560172 (Open Web Text)

Max Activating Token Index: 865

Text #6

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4510. Min Act: -0.1700

Data Index: 6036062 (Open Web Text)

Max Activating Token Index: 329

Text #7

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4455. Min Act: -0.1700

Data Index: 2922127 (Open Web Text)

Max Activating Token Index: 928

Text #8

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4483. Min Act: -0.1700

Data Index: 820539 (Open Web Text)

Max Activating Token Index: 593

Text #9

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4391. Min Act: -0.1700

Data Index: 4863684 (Open Web Text)

Max Activating Token Index: 910

Text #10

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4088. Min Act: -0.1700

Data Index: 7822837 (Open Web Text)

Max Activating Token Index: 368

Text #11

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4269. Min Act: -0.1700

Data Index: 4792329 (Open Web Text)

Max Activating Token Index: 697

Text #12

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4164. Min Act: -0.1700

Data Index: 1628005 (Open Web Text)

Max Activating Token Index: 661

Text #13

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4217. Min Act: -0.1700

Data Index: 4967236 (Open Web Text)

Max Activating Token Index: 493

Text #14

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4063. Min Act: -0.1700

Data Index: 8119006 (Open Web Text)

Max Activating Token Index: 133

Text #15

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.3807. Min Act: -0.1700

Data Index: 5465403 (Open Web Text)

Max Activating Token Index: 97

Text #16

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.3947. Min Act: -0.1700

Data Index: 1030145 (Open Web Text)

Max Activating Token Index: 185

Text #17

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.3912. Min Act: -0.1700

Data Index: 6427120 (Open Web Text)

Max Activating Token Index: 664

Text #18

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.3952. Min Act: -0.1700

Data Index: 2495567 (Open Web Text)

Max Activating Token Index: 995

Text #19

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.3822. Min Act: -0.1700

Data Index: 4329405 (Open Web Text)

Max Activating Token Index: 344