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

Dataset: Open Web Text

Neuron 953 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: 5.2005. Min Range: -5.2005

Max Act: 5.2005. Min Act: -0.1700

Data Index: 7301850 (Open Web Text)

Max Activating Token Index: 222

Text #1

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.8790. Min Act: -0.1700

Data Index: 8697348 (Open Web Text)

Max Activating Token Index: 48

Text #2

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.7632. Min Act: -0.1700

Data Index: 2713558 (Open Web Text)

Max Activating Token Index: 884

Text #3

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.8443. Min Act: -0.1700

Data Index: 5620471 (Open Web Text)

Max Activating Token Index: 138

Text #4

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.8633. Min Act: -0.1700

Data Index: 4038375 (Open Web Text)

Max Activating Token Index: 615

Text #5

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.7745. Min Act: -0.1700

Data Index: 5025351 (Open Web Text)

Max Activating Token Index: 939

Text #6

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.7722. Min Act: -0.1700

Data Index: 1043179 (Open Web Text)

Max Activating Token Index: 962

Text #7

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.8058. Min Act: -0.1700

Data Index: 1561995 (Open Web Text)

Max Activating Token Index: 667

Text #8

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.7903. Min Act: -0.1700

Data Index: 3227465 (Open Web Text)

Max Activating Token Index: 496

Text #9

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.8144. Min Act: -0.1700

Data Index: 5261905 (Open Web Text)

Max Activating Token Index: 780

Text #10

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.7856. Min Act: -0.1700

Data Index: 5321480 (Open Web Text)

Max Activating Token Index: 262

Text #11

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.8036. Min Act: -0.1700

Data Index: 8484633 (Open Web Text)

Max Activating Token Index: 564

Text #12

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.7933. Min Act: -0.1700

Data Index: 7923972 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.8400. Min Act: -0.1700

Data Index: 7629549 (Open Web Text)

Max Activating Token Index: 866

Text #14

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.7045. Min Act: -0.1700

Data Index: 3219998 (Open Web Text)

Max Activating Token Index: 853

Text #15

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.7814. Min Act: -0.1700

Data Index: 5108321 (Open Web Text)

Max Activating Token Index: 255

Text #16

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.7634. Min Act: -0.1700

Data Index: 2026553 (Open Web Text)

Max Activating Token Index: 568

Text #17

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.7593. Min Act: -0.1700

Data Index: 1269747 (Open Web Text)

Max Activating Token Index: 481

Text #18

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.7253. Min Act: -0.1700

Data Index: 5356722 (Open Web Text)

Max Activating Token Index: 261

Text #19

Max Range: 5.2005. Min Range: -5.2005

Max Act: 4.8022. Min Act: -0.1700

Data Index: 4250279 (Open Web Text)

Max Activating Token Index: 398