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

Dataset: Open Web Text

Neuron 2517 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: 3.1021. Min Range: -3.1021

Max Act: 3.1021. Min Act: -0.1700

Data Index: 7820296 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.1021. Min Range: -3.1021

Max Act: 3.0702. Min Act: -0.1700

Data Index: 8180652 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.1021. Min Range: -3.1021

Max Act: 3.0702. Min Act: -0.1700

Data Index: 7848439 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9828. Min Act: -0.1700

Data Index: 3057657 (Open Web Text)

Max Activating Token Index: 57

Text #4

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9925. Min Act: -0.1700

Data Index: 2248473 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9946. Min Act: -0.1700

Data Index: 5594235 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9776. Min Act: -0.1700

Data Index: 4363176 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9665. Min Act: -0.1700

Data Index: 5830893 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9796. Min Act: -0.1700

Data Index: 1528285 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9582. Min Act: -0.1700

Data Index: 806292 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9650. Min Act: -0.1700

Data Index: 2046723 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9613. Min Act: -0.1700

Data Index: 3628452 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9493. Min Act: -0.1700

Data Index: 7365766 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9562. Min Act: -0.1700

Data Index: 8075961 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9693. Min Act: -0.1700

Data Index: 7387613 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9444. Min Act: -0.1700

Data Index: 6684725 (Open Web Text)

Max Activating Token Index: 763

Text #16

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9473. Min Act: -0.1700

Data Index: 2523162 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9358. Min Act: -0.1700

Data Index: 129807 (Open Web Text)

Max Activating Token Index: 820

Text #18

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9422. Min Act: -0.1700

Data Index: 2894278 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9419. Min Act: -0.1700

Data Index: 8428669 (Open Web Text)

Max Activating Token Index: 6