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

Dataset: Open Web Text

Neuron 558 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: 3.0158. Min Range: -3.0158

Max Act: 3.0158. Min Act: -0.1700

Data Index: 4356541 (Open Web Text)

Max Activating Token Index: 381

Text #1

Max Range: 3.0158. Min Range: -3.0158

Max Act: 3.0013. Min Act: -0.1700

Data Index: 1200732 (Open Web Text)

Max Activating Token Index: 719

Text #2

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.9557. Min Act: -0.1700

Data Index: 6594195 (Open Web Text)

Max Activating Token Index: 208

Text #3

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.9649. Min Act: -0.1700

Data Index: 4499822 (Open Web Text)

Max Activating Token Index: 349

Text #4

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.9556. Min Act: -0.1700

Data Index: 3267719 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.9295. Min Act: -0.1700

Data Index: 6683621 (Open Web Text)

Max Activating Token Index: 272

Text #6

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.9218. Min Act: -0.1700

Data Index: 7674521 (Open Web Text)

Max Activating Token Index: 951

Text #7

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.8539. Min Act: -0.1700

Data Index: 8583473 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.8496. Min Act: -0.1700

Data Index: 1616582 (Open Web Text)

Max Activating Token Index: 62

Text #9

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.8428. Min Act: -0.1700

Data Index: 6712909 (Open Web Text)

Max Activating Token Index: 559

Text #10

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.8240. Min Act: -0.1700

Data Index: 8032296 (Open Web Text)

Max Activating Token Index: 20

Text #11

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.8182. Min Act: -0.1700

Data Index: 5560579 (Open Web Text)

Max Activating Token Index: 690

Text #12

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.8118. Min Act: -0.1700

Data Index: 3834030 (Open Web Text)

Max Activating Token Index: 755

Text #13

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7823. Min Act: -0.1700

Data Index: 3547118 (Open Web Text)

Max Activating Token Index: 784

Text #14

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7854. Min Act: -0.1700

Data Index: 6198875 (Open Web Text)

Max Activating Token Index: 260

Text #15

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7993. Min Act: -0.1700

Data Index: 4499825 (Open Web Text)

Max Activating Token Index: 199

Text #16

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7684. Min Act: -0.1700

Data Index: 3088912 (Open Web Text)

Max Activating Token Index: 222

Text #17

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7614. Min Act: -0.1700

Data Index: 3402580 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7767. Min Act: -0.1700

Data Index: 6287396 (Open Web Text)

Max Activating Token Index: 813

Text #19

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7789. Min Act: -0.1700

Data Index: 1215160 (Open Web Text)

Max Activating Token Index: 978