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

Dataset: Open Web Text

Neuron 2042 in Layer 0

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: 0.0964. Min Range: -0.0964

Max Act: 0.0964. Min Act: -0.1680

Data Index: 3705346 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0859. Min Act: -0.1700

Data Index: 5813305 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0639. Min Act: -0.1699

Data Index: 1865844 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0657. Min Act: -0.1700

Data Index: 1628468 (Open Web Text)

Max Activating Token Index: 966

Text #4

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0652. Min Act: -0.1700

Data Index: 3814914 (Open Web Text)

Max Activating Token Index: 873

Text #5

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0582. Min Act: -0.1699

Data Index: 5065279 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0618. Min Act: -0.1696

Data Index: 7384049 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0523. Min Act: -0.1657

Data Index: 8277290 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0522. Min Act: -0.1696

Data Index: 3150450 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0531. Min Act: -0.1698

Data Index: 4311593 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0446. Min Act: -0.1700

Data Index: 768611 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0496. Min Act: -0.1699

Data Index: 6457291 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0440. Min Act: -0.1685

Data Index: 5900603 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0401. Min Act: -0.1700

Data Index: 6572900 (Open Web Text)

Max Activating Token Index: 325

Text #14

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0357. Min Act: -0.1648

Data Index: 1955859 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0339. Min Act: -0.1644

Data Index: 530518 (Open Web Text)

Max Activating Token Index: 863

Text #16

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0318. Min Act: -0.1692

Data Index: 4447750 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0374. Min Act: -0.1700

Data Index: 6837216 (Open Web Text)

Max Activating Token Index: 920

Text #18

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0301. Min Act: -0.1693

Data Index: 2594595 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0308. Min Act: -0.1672

Data Index: 4062078 (Open Web Text)

Max Activating Token Index: 3