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

Dataset: Open Web Text

Neuron 186 in Layer 4

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: 3.0802. Min Range: -3.0802

Max Act: 3.0802. Min Act: -0.1700

Data Index: 6212334 (Open Web Text)

Max Activating Token Index: 867

Text #1

Max Range: 3.0802. Min Range: -3.0802

Max Act: 3.0637. Min Act: -0.1700

Data Index: 3720176 (Open Web Text)

Max Activating Token Index: 723

Text #2

Max Range: 3.0802. Min Range: -3.0802

Max Act: 3.0347. Min Act: -0.1700

Data Index: 3792301 (Open Web Text)

Max Activating Token Index: 483

Text #3

Max Range: 3.0802. Min Range: -3.0802

Max Act: 3.0300. Min Act: -0.1700

Data Index: 1147278 (Open Web Text)

Max Activating Token Index: 852

Text #4

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9948. Min Act: -0.1700

Data Index: 6163418 (Open Web Text)

Max Activating Token Index: 603

Text #5

Max Range: 3.0802. Min Range: -3.0802

Max Act: 3.0025. Min Act: -0.1700

Data Index: 8813020 (Open Web Text)

Max Activating Token Index: 818

Text #6

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9990. Min Act: -0.1700

Data Index: 4302649 (Open Web Text)

Max Activating Token Index: 564

Text #7

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9927. Min Act: -0.1700

Data Index: 4875434 (Open Web Text)

Max Activating Token Index: 824

Text #8

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9763. Min Act: -0.1700

Data Index: 2374549 (Open Web Text)

Max Activating Token Index: 107

Text #9

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9437. Min Act: -0.1700

Data Index: 802107 (Open Web Text)

Max Activating Token Index: 633

Text #10

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9653. Min Act: -0.1700

Data Index: 3397939 (Open Web Text)

Max Activating Token Index: 614

Text #11

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9479. Min Act: -0.1700

Data Index: 8652081 (Open Web Text)

Max Activating Token Index: 679

Text #12

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9459. Min Act: -0.1700

Data Index: 1010325 (Open Web Text)

Max Activating Token Index: 549

Text #13

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9653. Min Act: -0.1700

Data Index: 8316844 (Open Web Text)

Max Activating Token Index: 654

Text #14

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9344. Min Act: -0.1700

Data Index: 5995899 (Open Web Text)

Max Activating Token Index: 360

Text #15

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9390. Min Act: -0.1700

Data Index: 1687683 (Open Web Text)

Max Activating Token Index: 485

Text #16

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9479. Min Act: -0.1700

Data Index: 8129456 (Open Web Text)

Max Activating Token Index: 853

Text #17

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9504. Min Act: -0.1700

Data Index: 1687682 (Open Web Text)

Max Activating Token Index: 760

Text #18

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9356. Min Act: -0.1700

Data Index: 7302462 (Open Web Text)

Max Activating Token Index: 572

Text #19

Max Range: 3.0802. Min Range: -3.0802

Max Act: 2.9301. Min Act: -0.1700

Data Index: 6877438 (Open Web Text)

Max Activating Token Index: 93