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

Dataset: Open Web Text

Neuron 1016 in Layer 6

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: 3.8977. Min Range: -3.8977

Max Act: 3.8977. Min Act: -0.1700

Data Index: 2822714 (Open Web Text)

Max Activating Token Index: 157

Text #1

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.8705. Min Act: -0.1700

Data Index: 1995518 (Open Web Text)

Max Activating Token Index: 514

Text #2

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.8615. Min Act: -0.1700

Data Index: 7123431 (Open Web Text)

Max Activating Token Index: 203

Text #3

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.8195. Min Act: -0.1700

Data Index: 4901535 (Open Web Text)

Max Activating Token Index: 502

Text #4

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.8187. Min Act: -0.1700

Data Index: 5512795 (Open Web Text)

Max Activating Token Index: 195

Text #5

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.7757. Min Act: -0.1700

Data Index: 7930805 (Open Web Text)

Max Activating Token Index: 941

Text #6

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.7752. Min Act: -0.1700

Data Index: 8695126 (Open Web Text)

Max Activating Token Index: 613

Text #7

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.7713. Min Act: -0.1700

Data Index: 4418029 (Open Web Text)

Max Activating Token Index: 998

Text #8

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.7670. Min Act: -0.1700

Data Index: 3817379 (Open Web Text)

Max Activating Token Index: 1004

Text #9

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.7202. Min Act: -0.1700

Data Index: 7497368 (Open Web Text)

Max Activating Token Index: 802

Text #10

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.6975. Min Act: -0.1700

Data Index: 5980560 (Open Web Text)

Max Activating Token Index: 517

Text #11

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.7083. Min Act: -0.1700

Data Index: 3031081 (Open Web Text)

Max Activating Token Index: 766

Text #12

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.7035. Min Act: -0.1700

Data Index: 6691621 (Open Web Text)

Max Activating Token Index: 815

Text #13

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.7065. Min Act: -0.1700

Data Index: 6459557 (Open Web Text)

Max Activating Token Index: 959

Text #14

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.7120. Min Act: -0.1700

Data Index: 4177536 (Open Web Text)

Max Activating Token Index: 809

Text #15

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.6824. Min Act: -0.1700

Data Index: 2391888 (Open Web Text)

Max Activating Token Index: 722

Text #16

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.7051. Min Act: -0.1700

Data Index: 950625 (Open Web Text)

Max Activating Token Index: 692

Text #17

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.6729. Min Act: -0.1700

Data Index: 5062378 (Open Web Text)

Max Activating Token Index: 721

Text #18

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.6627. Min Act: -0.1700

Data Index: 5583524 (Open Web Text)

Max Activating Token Index: 607

Text #19

Max Range: 3.8977. Min Range: -3.8977

Max Act: 3.6435. Min Act: -0.1700

Data Index: 826823 (Open Web Text)

Max Activating Token Index: 841