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

Dataset: Open Web Text

Neuron 269 in Layer 6

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: 4.0960. Min Range: -4.0960

Max Act: 4.0960. Min Act: -0.1700

Data Index: 7720338 (Open Web Text)

Max Activating Token Index: 794

Text #1

Max Range: 4.0960. Min Range: -4.0960

Max Act: 4.0764. Min Act: -0.1700

Data Index: 3397123 (Open Web Text)

Max Activating Token Index: 691

Text #2

Max Range: 4.0960. Min Range: -4.0960

Max Act: 4.0804. Min Act: -0.1700

Data Index: 1041985 (Open Web Text)

Max Activating Token Index: 913

Text #3

Max Range: 4.0960. Min Range: -4.0960

Max Act: 4.0738. Min Act: -0.1700

Data Index: 7579522 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 4.0960. Min Range: -4.0960

Max Act: 4.0316. Min Act: -0.1700

Data Index: 1869749 (Open Web Text)

Max Activating Token Index: 514

Text #5

Max Range: 4.0960. Min Range: -4.0960

Max Act: 4.0103. Min Act: -0.1700

Data Index: 760940 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.0960. Min Range: -4.0960

Max Act: 4.0110. Min Act: -0.1700

Data Index: 4229202 (Open Web Text)

Max Activating Token Index: 952

Text #7

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9725. Min Act: -0.1700

Data Index: 2947137 (Open Web Text)

Max Activating Token Index: 947

Text #8

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9554. Min Act: -0.1700

Data Index: 5096765 (Open Web Text)

Max Activating Token Index: 944

Text #9

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9704. Min Act: -0.1700

Data Index: 1995554 (Open Web Text)

Max Activating Token Index: 885

Text #10

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9715. Min Act: -0.1700

Data Index: 4557801 (Open Web Text)

Max Activating Token Index: 911

Text #11

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9903. Min Act: -0.1700

Data Index: 8829822 (Open Web Text)

Max Activating Token Index: 260

Text #12

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9872. Min Act: -0.1700

Data Index: 8189323 (Open Web Text)

Max Activating Token Index: 136

Text #13

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9552. Min Act: -0.1700

Data Index: 7727807 (Open Web Text)

Max Activating Token Index: 878

Text #14

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9562. Min Act: -0.1700

Data Index: 533134 (Open Web Text)

Max Activating Token Index: 596

Text #15

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9573. Min Act: -0.1700

Data Index: 7063566 (Open Web Text)

Max Activating Token Index: 452

Text #16

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9612. Min Act: -0.1700

Data Index: 6774489 (Open Web Text)

Max Activating Token Index: 457

Text #17

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9360. Min Act: -0.1700

Data Index: 1969438 (Open Web Text)

Max Activating Token Index: 893

Text #18

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9274. Min Act: -0.1700

Data Index: 1381886 (Open Web Text)

Max Activating Token Index: 705

Text #19

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9275. Min Act: -0.1700

Data Index: 5844269 (Open Web Text)

Max Activating Token Index: 531