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

Dataset: Open Web Text

Neuron 391 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: 0.6894. Min Range: -0.6894

Max Act: 0.6894. Min Act: -0.1700

Data Index: 5692374 (Open Web Text)

Max Activating Token Index: 998

Text #1

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.6804. Min Act: -0.1700

Data Index: 4766535 (Open Web Text)

Max Activating Token Index: 638

Text #2

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5989. Min Act: -0.1700

Data Index: 5957659 (Open Web Text)

Max Activating Token Index: 620

Text #3

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5821. Min Act: -0.1700

Data Index: 3622819 (Open Web Text)

Max Activating Token Index: 910

Text #4

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5674. Min Act: -0.1700

Data Index: 7076388 (Open Web Text)

Max Activating Token Index: 557

Text #5

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5509. Min Act: -0.1700

Data Index: 4427070 (Open Web Text)

Max Activating Token Index: 734

Text #6

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5318. Min Act: -0.1700

Data Index: 1900262 (Open Web Text)

Max Activating Token Index: 989

Text #7

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5217. Min Act: -0.1686

Data Index: 5599180 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5227. Min Act: -0.1700

Data Index: 8822302 (Open Web Text)

Max Activating Token Index: 734

Text #9

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5185. Min Act: -0.1700

Data Index: 3261406 (Open Web Text)

Max Activating Token Index: 526

Text #10

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4933. Min Act: -0.1695

Data Index: 5185694 (Open Web Text)

Max Activating Token Index: 1017

Text #11

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4965. Min Act: -0.1700

Data Index: 8136727 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5044. Min Act: -0.1700

Data Index: 5038843 (Open Web Text)

Max Activating Token Index: 896

Text #13

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5078. Min Act: -0.1700

Data Index: 7654392 (Open Web Text)

Max Activating Token Index: 481

Text #14

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4961. Min Act: -0.1700

Data Index: 1984651 (Open Web Text)

Max Activating Token Index: 652

Text #15

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4854. Min Act: -0.1700

Data Index: 5180257 (Open Web Text)

Max Activating Token Index: 625

Text #16

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5079. Min Act: -0.1700

Data Index: 6108356 (Open Web Text)

Max Activating Token Index: 1002

Text #17

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4813. Min Act: -0.1700

Data Index: 3783024 (Open Web Text)

Max Activating Token Index: 501

Text #18

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4765. Min Act: -0.1700

Data Index: 8817258 (Open Web Text)

Max Activating Token Index: 769

Text #19

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4810. Min Act: -0.1700

Data Index: 4763305 (Open Web Text)

Max Activating Token Index: 491