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

Dataset: Open Web Text

Neuron 1691 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: 4.0966. Min Range: -4.0966

Max Act: 4.0966. Min Act: -0.1700

Data Index: 6111219 (Open Web Text)

Max Activating Token Index: 716

Text #1

Max Range: 4.0966. Min Range: -4.0966

Max Act: 4.0787. Min Act: -0.1700

Data Index: 2940359 (Open Web Text)

Max Activating Token Index: 463

Text #2

Max Range: 4.0966. Min Range: -4.0966

Max Act: 4.0950. Min Act: -0.1700

Data Index: 6780588 (Open Web Text)

Max Activating Token Index: 833

Text #3

Max Range: 4.0966. Min Range: -4.0966

Max Act: 4.0625. Min Act: -0.1700

Data Index: 7181530 (Open Web Text)

Max Activating Token Index: 782

Text #4

Max Range: 4.0966. Min Range: -4.0966

Max Act: 4.0652. Min Act: -0.1700

Data Index: 7900353 (Open Web Text)

Max Activating Token Index: 961

Text #5

Max Range: 4.0966. Min Range: -4.0966

Max Act: 4.0786. Min Act: -0.1700

Data Index: 2064938 (Open Web Text)

Max Activating Token Index: 830

Text #6

Max Range: 4.0966. Min Range: -4.0966

Max Act: 4.0148. Min Act: -0.1700

Data Index: 6299630 (Open Web Text)

Max Activating Token Index: 62

Text #7

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.9816. Min Act: -0.1700

Data Index: 7567859 (Open Web Text)

Max Activating Token Index: 982

Text #8

Max Range: 4.0966. Min Range: -4.0966

Max Act: 4.0166. Min Act: -0.1700

Data Index: 1293530 (Open Web Text)

Max Activating Token Index: 1002

Text #9

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.9776. Min Act: -0.1700

Data Index: 5223147 (Open Web Text)

Max Activating Token Index: 362

Text #10

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.9875. Min Act: -0.1700

Data Index: 5941771 (Open Web Text)

Max Activating Token Index: 277

Text #11

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.9884. Min Act: -0.1700

Data Index: 7844784 (Open Web Text)

Max Activating Token Index: 120

Text #12

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.9912. Min Act: -0.1700

Data Index: 7655846 (Open Web Text)

Max Activating Token Index: 460

Text #13

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.9526. Min Act: -0.1700

Data Index: 6330249 (Open Web Text)

Max Activating Token Index: 353

Text #14

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.9307. Min Act: -0.1700

Data Index: 5470561 (Open Web Text)

Max Activating Token Index: 263

Text #15

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.9374. Min Act: -0.1700

Data Index: 1584245 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.9560. Min Act: -0.1700

Data Index: 6631075 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.9747. Min Act: -0.1700

Data Index: 1460668 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.9724. Min Act: -0.1700

Data Index: 8152570 (Open Web Text)

Max Activating Token Index: 464

Text #19

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.9421. Min Act: -0.1700

Data Index: 254423 (Open Web Text)

Max Activating Token Index: 1009