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

Dataset: Open Web Text

Neuron 726 in Layer 4

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: 4.0181. Min Range: -4.0181

Max Act: 4.0181. Min Act: -0.1700

Data Index: 4028991 (Open Web Text)

Max Activating Token Index: 872

Text #1

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.9985. Min Act: -0.1700

Data Index: 3803704 (Open Web Text)

Max Activating Token Index: 691

Text #2

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.9094. Min Act: -0.1700

Data Index: 2826056 (Open Web Text)

Max Activating Token Index: 538

Text #3

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.9439. Min Act: -0.1700

Data Index: 3496106 (Open Web Text)

Max Activating Token Index: 771

Text #4

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.9798. Min Act: -0.1700

Data Index: 7886118 (Open Web Text)

Max Activating Token Index: 467

Text #5

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8827. Min Act: -0.1700

Data Index: 2231681 (Open Web Text)

Max Activating Token Index: 776

Text #6

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8616. Min Act: -0.1700

Data Index: 2432476 (Open Web Text)

Max Activating Token Index: 682

Text #7

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8846. Min Act: -0.1700

Data Index: 770333 (Open Web Text)

Max Activating Token Index: 127

Text #8

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8852. Min Act: -0.1700

Data Index: 8195364 (Open Web Text)

Max Activating Token Index: 250

Text #9

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8404. Min Act: -0.1700

Data Index: 6325444 (Open Web Text)

Max Activating Token Index: 296

Text #10

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8762. Min Act: -0.1700

Data Index: 7823357 (Open Web Text)

Max Activating Token Index: 734

Text #11

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8213. Min Act: -0.1700

Data Index: 3686363 (Open Web Text)

Max Activating Token Index: 618

Text #12

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8674. Min Act: -0.1700

Data Index: 5843549 (Open Web Text)

Max Activating Token Index: 437

Text #13

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8756. Min Act: -0.1700

Data Index: 2605560 (Open Web Text)

Max Activating Token Index: 120

Text #14

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8261. Min Act: -0.1700

Data Index: 4480243 (Open Web Text)

Max Activating Token Index: 665

Text #15

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8427. Min Act: -0.1700

Data Index: 3058919 (Open Web Text)

Max Activating Token Index: 86

Text #16

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8338. Min Act: -0.1700

Data Index: 2350744 (Open Web Text)

Max Activating Token Index: 752

Text #17

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8306. Min Act: -0.1700

Data Index: 2437138 (Open Web Text)

Max Activating Token Index: 576

Text #18

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.7977. Min Act: -0.1700

Data Index: 1573614 (Open Web Text)

Max Activating Token Index: 824

Text #19

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8345. Min Act: -0.1700

Data Index: 4733751 (Open Web Text)

Max Activating Token Index: 64