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

Dataset: Open Web Text

Neuron 1066 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: 4.5529. Min Range: -4.5529

Max Act: 4.5232. Min Act: -0.1700

Data Index: 5614465 (Open Web Text)

Max Activating Token Index: 553

Text #1

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.5529. Min Act: -0.1700

Data Index: 2895537 (Open Web Text)

Max Activating Token Index: 425

Text #2

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.5443. Min Act: -0.1700

Data Index: 1820316 (Open Web Text)

Max Activating Token Index: 175

Text #3

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.4813. Min Act: -0.1700

Data Index: 7211399 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.4561. Min Act: -0.1700

Data Index: 8205251 (Open Web Text)

Max Activating Token Index: 753

Text #5

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3861. Min Act: -0.1700

Data Index: 7569747 (Open Web Text)

Max Activating Token Index: 1007

Text #6

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3589. Min Act: -0.1700

Data Index: 8342081 (Open Web Text)

Max Activating Token Index: 729

Text #7

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3861. Min Act: -0.1700

Data Index: 8161043 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3899. Min Act: -0.1700

Data Index: 1113015 (Open Web Text)

Max Activating Token Index: 184

Text #9

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.4015. Min Act: -0.1700

Data Index: 3286693 (Open Web Text)

Max Activating Token Index: 198

Text #10

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3769. Min Act: -0.1700

Data Index: 5479972 (Open Web Text)

Max Activating Token Index: 49

Text #11

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3595. Min Act: -0.1700

Data Index: 3391921 (Open Web Text)

Max Activating Token Index: 409

Text #12

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3919. Min Act: -0.1700

Data Index: 8013437 (Open Web Text)

Max Activating Token Index: 570

Text #13

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3589. Min Act: -0.1700

Data Index: 7899647 (Open Web Text)

Max Activating Token Index: 226

Text #14

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3718. Min Act: -0.1700

Data Index: 7333222 (Open Web Text)

Max Activating Token Index: 467

Text #15

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3742. Min Act: -0.1700

Data Index: 7314156 (Open Web Text)

Max Activating Token Index: 401

Text #16

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3633. Min Act: -0.1700

Data Index: 4827555 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3221. Min Act: -0.1700

Data Index: 7246525 (Open Web Text)

Max Activating Token Index: 516

Text #18

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3766. Min Act: -0.1700

Data Index: 566642 (Open Web Text)

Max Activating Token Index: 534

Text #19

Max Range: 4.5529. Min Range: -4.5529

Max Act: 4.3719. Min Act: -0.1700

Data Index: 6767082 (Open Web Text)

Max Activating Token Index: 142