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

Dataset: Open Web Text

Neuron 3031 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: 4.0232. Min Range: -4.0232

Max Act: 4.0232. Min Act: -0.1700

Data Index: 6929833 (Open Web Text)

Max Activating Token Index: 237

Text #1

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.9910. Min Act: -0.1700

Data Index: 775870 (Open Web Text)

Max Activating Token Index: 685

Text #2

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.9624. Min Act: -0.1700

Data Index: 846640 (Open Web Text)

Max Activating Token Index: 856

Text #3

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.9029. Min Act: -0.1700

Data Index: 6927952 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.8925. Min Act: -0.1700

Data Index: 2876482 (Open Web Text)

Max Activating Token Index: 128

Text #5

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.8404. Min Act: -0.1700

Data Index: 3545785 (Open Web Text)

Max Activating Token Index: 910

Text #6

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.8325. Min Act: -0.1700

Data Index: 2191727 (Open Web Text)

Max Activating Token Index: 136

Text #7

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.8141. Min Act: -0.1700

Data Index: 4784656 (Open Web Text)

Max Activating Token Index: 104

Text #8

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.7796. Min Act: -0.1700

Data Index: 813775 (Open Web Text)

Max Activating Token Index: 662

Text #9

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.8021. Min Act: -0.1700

Data Index: 2703726 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.8246. Min Act: -0.1700

Data Index: 8189782 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.8271. Min Act: -0.1700

Data Index: 4032605 (Open Web Text)

Max Activating Token Index: 331

Text #12

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.8112. Min Act: -0.1700

Data Index: 1402002 (Open Web Text)

Max Activating Token Index: 145

Text #13

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.8007. Min Act: -0.1700

Data Index: 3563725 (Open Web Text)

Max Activating Token Index: 212

Text #14

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.7643. Min Act: -0.1700

Data Index: 6546323 (Open Web Text)

Max Activating Token Index: 915

Text #15

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.7669. Min Act: -0.1700

Data Index: 1517865 (Open Web Text)

Max Activating Token Index: 853

Text #16

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.7621. Min Act: -0.1700

Data Index: 7886046 (Open Web Text)

Max Activating Token Index: 968

Text #17

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.7757. Min Act: -0.1700

Data Index: 5169486 (Open Web Text)

Max Activating Token Index: 467

Text #18

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.7547. Min Act: -0.1700

Data Index: 4807560 (Open Web Text)

Max Activating Token Index: 1000

Text #19

Max Range: 4.0232. Min Range: -4.0232

Max Act: 3.7269. Min Act: -0.1700

Data Index: 4722400 (Open Web Text)

Max Activating Token Index: 599