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

Dataset: Open Web Text

Neuron 2084 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: 3.0303. Min Range: -3.0303

Max Act: 3.0303. Min Act: -0.1700

Data Index: 8730373 (Open Web Text)

Max Activating Token Index: 776

Text #1

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9768. Min Act: -0.1700

Data Index: 3643478 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9813. Min Act: -0.1700

Data Index: 2046645 (Open Web Text)

Max Activating Token Index: 360

Text #3

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9768. Min Act: -0.1700

Data Index: 4659941 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9785. Min Act: -0.1700

Data Index: 772861 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9768. Min Act: -0.1700

Data Index: 6302582 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9768. Min Act: -0.1700

Data Index: 6657686 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9768. Min Act: -0.1700

Data Index: 182236 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9768. Min Act: -0.1700

Data Index: 858896 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9768. Min Act: -0.1700

Data Index: 8537951 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9768. Min Act: -0.1700

Data Index: 2247198 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9768. Min Act: -0.1700

Data Index: 8231216 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9768. Min Act: -0.1700

Data Index: 2117802 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9809. Min Act: -0.1700

Data Index: 8411736 (Open Web Text)

Max Activating Token Index: 402

Text #14

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9470. Min Act: -0.1700

Data Index: 5746157 (Open Web Text)

Max Activating Token Index: 276

Text #15

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9435. Min Act: -0.1700

Data Index: 7481319 (Open Web Text)

Max Activating Token Index: 527

Text #16

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9036. Min Act: -0.1700

Data Index: 4646434 (Open Web Text)

Max Activating Token Index: 174

Text #17

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9073. Min Act: -0.1700

Data Index: 55429 (Open Web Text)

Max Activating Token Index: 428

Text #18

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9394. Min Act: -0.1700

Data Index: 4761429 (Open Web Text)

Max Activating Token Index: 540

Text #19

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8941. Min Act: -0.1700

Data Index: 6352101 (Open Web Text)

Max Activating Token Index: 316