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

Dataset: Open Web Text

Neuron 1048 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: 3.4553. Min Range: -3.4553

Max Act: 3.4493. Min Act: -0.1700

Data Index: 3114974 (Open Web Text)

Max Activating Token Index: 946

Text #1

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.4553. Min Act: -0.1700

Data Index: 4064382 (Open Web Text)

Max Activating Token Index: 131

Text #2

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.4425. Min Act: -0.1700

Data Index: 2748324 (Open Web Text)

Max Activating Token Index: 326

Text #3

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.4167. Min Act: -0.1700

Data Index: 1950437 (Open Web Text)

Max Activating Token Index: 136

Text #4

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.4076. Min Act: -0.1700

Data Index: 5958898 (Open Web Text)

Max Activating Token Index: 564

Text #5

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3841. Min Act: -0.1700

Data Index: 4981624 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3933. Min Act: -0.1700

Data Index: 1846199 (Open Web Text)

Max Activating Token Index: 155

Text #7

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3923. Min Act: -0.1700

Data Index: 5594864 (Open Web Text)

Max Activating Token Index: 121

Text #8

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3730. Min Act: -0.1700

Data Index: 2183652 (Open Web Text)

Max Activating Token Index: 29

Text #9

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3597. Min Act: -0.1700

Data Index: 430883 (Open Web Text)

Max Activating Token Index: 21

Text #10

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3777. Min Act: -0.1700

Data Index: 8232927 (Open Web Text)

Max Activating Token Index: 713

Text #11

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3622. Min Act: -0.1700

Data Index: 4421127 (Open Web Text)

Max Activating Token Index: 1012

Text #12

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3566. Min Act: -0.1700

Data Index: 1891836 (Open Web Text)

Max Activating Token Index: 826

Text #13

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3747. Min Act: -0.1700

Data Index: 3743325 (Open Web Text)

Max Activating Token Index: 330

Text #14

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3483. Min Act: -0.1700

Data Index: 1345686 (Open Web Text)

Max Activating Token Index: 840

Text #15

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3439. Min Act: -0.1700

Data Index: 5403820 (Open Web Text)

Max Activating Token Index: 589

Text #16

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3449. Min Act: -0.1700

Data Index: 663921 (Open Web Text)

Max Activating Token Index: 610

Text #17

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3545. Min Act: -0.1700

Data Index: 5970830 (Open Web Text)

Max Activating Token Index: 143

Text #18

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3559. Min Act: -0.1700

Data Index: 2652804 (Open Web Text)

Max Activating Token Index: 354

Text #19

Max Range: 3.4553. Min Range: -3.4553

Max Act: 3.3310. Min Act: -0.1700

Data Index: 5904451 (Open Web Text)

Max Activating Token Index: 1021