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

Dataset: Open Web Text

Neuron 440 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: 4.7498. Min Range: -4.7498

Max Act: 4.7452. Min Act: -0.1700

Data Index: 8229538 (Open Web Text)

Max Activating Token Index: 227

Text #1

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.7498. Min Act: -0.1700

Data Index: 8513953 (Open Web Text)

Max Activating Token Index: 457

Text #2

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.6865. Min Act: -0.1700

Data Index: 4628113 (Open Web Text)

Max Activating Token Index: 491

Text #3

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.7312. Min Act: -0.1700

Data Index: 3479162 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.6948. Min Act: -0.1700

Data Index: 671454 (Open Web Text)

Max Activating Token Index: 73

Text #5

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.7171. Min Act: -0.1700

Data Index: 8713393 (Open Web Text)

Max Activating Token Index: 589

Text #6

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.7023. Min Act: -0.1700

Data Index: 7063116 (Open Web Text)

Max Activating Token Index: 175

Text #7

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.6897. Min Act: -0.1700

Data Index: 7060159 (Open Web Text)

Max Activating Token Index: 658

Text #8

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.6885. Min Act: -0.1700

Data Index: 197514 (Open Web Text)

Max Activating Token Index: 492

Text #9

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.7097. Min Act: -0.1700

Data Index: 8450294 (Open Web Text)

Max Activating Token Index: 723

Text #10

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.6536. Min Act: -0.1700

Data Index: 8000416 (Open Web Text)

Max Activating Token Index: 636

Text #11

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.6226. Min Act: -0.1700

Data Index: 6202996 (Open Web Text)

Max Activating Token Index: 136

Text #12

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.6127. Min Act: -0.1700

Data Index: 3597070 (Open Web Text)

Max Activating Token Index: 332

Text #13

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.6536. Min Act: -0.1700

Data Index: 4237272 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.5940. Min Act: -0.1700

Data Index: 1466943 (Open Web Text)

Max Activating Token Index: 31

Text #15

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.6406. Min Act: -0.1700

Data Index: 3049321 (Open Web Text)

Max Activating Token Index: 540

Text #16

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.5977. Min Act: -0.1700

Data Index: 4114684 (Open Web Text)

Max Activating Token Index: 487

Text #17

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.6093. Min Act: -0.1700

Data Index: 3666329 (Open Web Text)

Max Activating Token Index: 736

Text #18

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.5761. Min Act: -0.1700

Data Index: 336304 (Open Web Text)

Max Activating Token Index: 719

Text #19

Max Range: 4.7498. Min Range: -4.7498

Max Act: 4.5619. Min Act: -0.1700

Data Index: 6686324 (Open Web Text)

Max Activating Token Index: 179