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

Dataset: Open Web Text

Neuron 2939 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: 3.4569. Min Range: -3.4569

Max Act: 3.4569. Min Act: -0.1700

Data Index: 1456510 (Open Web Text)

Max Activating Token Index: 434

Text #1

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.4321. Min Act: -0.1700

Data Index: 7129125 (Open Web Text)

Max Activating Token Index: 717

Text #2

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.4370. Min Act: -0.1700

Data Index: 2545141 (Open Web Text)

Max Activating Token Index: 411

Text #3

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.4015. Min Act: -0.1700

Data Index: 5898262 (Open Web Text)

Max Activating Token Index: 616

Text #4

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.4067. Min Act: -0.1700

Data Index: 7427356 (Open Web Text)

Max Activating Token Index: 997

Text #5

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3957. Min Act: -0.1700

Data Index: 6403221 (Open Web Text)

Max Activating Token Index: 143

Text #6

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3977. Min Act: -0.1700

Data Index: 5604286 (Open Web Text)

Max Activating Token Index: 737

Text #7

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3840. Min Act: -0.1700

Data Index: 8447492 (Open Web Text)

Max Activating Token Index: 937

Text #8

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3608. Min Act: -0.1700

Data Index: 2515082 (Open Web Text)

Max Activating Token Index: 58

Text #9

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3440. Min Act: -0.1700

Data Index: 5145948 (Open Web Text)

Max Activating Token Index: 793

Text #10

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3562. Min Act: -0.1700

Data Index: 6235537 (Open Web Text)

Max Activating Token Index: 198

Text #11

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3709. Min Act: -0.1700

Data Index: 1383809 (Open Web Text)

Max Activating Token Index: 627

Text #12

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3463. Min Act: -0.1700

Data Index: 901540 (Open Web Text)

Max Activating Token Index: 543

Text #13

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3534. Min Act: -0.1700

Data Index: 4993376 (Open Web Text)

Max Activating Token Index: 326

Text #14

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3437. Min Act: -0.1700

Data Index: 5087282 (Open Web Text)

Max Activating Token Index: 626

Text #15

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3444. Min Act: -0.1700

Data Index: 8510034 (Open Web Text)

Max Activating Token Index: 707

Text #16

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3357. Min Act: -0.1700

Data Index: 5636461 (Open Web Text)

Max Activating Token Index: 514

Text #17

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3411. Min Act: -0.1700

Data Index: 2946916 (Open Web Text)

Max Activating Token Index: 357

Text #18

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3184. Min Act: -0.1700

Data Index: 5137803 (Open Web Text)

Max Activating Token Index: 790

Text #19

Max Range: 3.4569. Min Range: -3.4569

Max Act: 3.3158. Min Act: -0.1700

Data Index: 7896338 (Open Web Text)

Max Activating Token Index: 911