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

Dataset: Open Web Text

Neuron 725 in Layer 5

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: 4.5645. Min Range: -4.5645

Max Act: 4.5645. Min Act: -0.1700

Data Index: 6077637 (Open Web Text)

Max Activating Token Index: 778

Text #1

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.4970. Min Act: -0.1700

Data Index: 2389818 (Open Web Text)

Max Activating Token Index: 1013

Text #2

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.4487. Min Act: -0.1700

Data Index: 2264145 (Open Web Text)

Max Activating Token Index: 967

Text #3

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.4359. Min Act: -0.1700

Data Index: 5150730 (Open Web Text)

Max Activating Token Index: 721

Text #4

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.4015. Min Act: -0.1700

Data Index: 4803795 (Open Web Text)

Max Activating Token Index: 258

Text #5

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.4193. Min Act: -0.1700

Data Index: 5897954 (Open Web Text)

Max Activating Token Index: 978

Text #6

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.4127. Min Act: -0.1700

Data Index: 719163 (Open Web Text)

Max Activating Token Index: 889

Text #7

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.4247. Min Act: -0.1700

Data Index: 2032750 (Open Web Text)

Max Activating Token Index: 629

Text #8

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.4080. Min Act: -0.1700

Data Index: 8402429 (Open Web Text)

Max Activating Token Index: 649

Text #9

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.3848. Min Act: -0.1700

Data Index: 7728562 (Open Web Text)

Max Activating Token Index: 827

Text #10

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.3065. Min Act: -0.1700

Data Index: 5392063 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.3721. Min Act: -0.1700

Data Index: 3872412 (Open Web Text)

Max Activating Token Index: 30

Text #12

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.3489. Min Act: -0.1700

Data Index: 2918339 (Open Web Text)

Max Activating Token Index: 1003

Text #13

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.2973. Min Act: -0.1700

Data Index: 117737 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.3243. Min Act: -0.1700

Data Index: 3261383 (Open Web Text)

Max Activating Token Index: 272

Text #15

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.2807. Min Act: -0.1700

Data Index: 2067771 (Open Web Text)

Max Activating Token Index: 962

Text #16

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.2906. Min Act: -0.1700

Data Index: 1274055 (Open Web Text)

Max Activating Token Index: 468

Text #17

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.2843. Min Act: -0.1700

Data Index: 2370859 (Open Web Text)

Max Activating Token Index: 371

Text #18

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.2714. Min Act: -0.1700

Data Index: 4177420 (Open Web Text)

Max Activating Token Index: 566

Text #19

Max Range: 4.5645. Min Range: -4.5645

Max Act: 4.2583. Min Act: -0.1700

Data Index: 6028252 (Open Web Text)

Max Activating Token Index: 559