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

Dataset: Open Web Text

Neuron 1220 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: 3.2558. Min Range: -3.2558

Max Act: 3.2558. Min Act: -0.1700

Data Index: 2933948 (Open Web Text)

Max Activating Token Index: 142

Text #1

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.2450. Min Act: -0.1700

Data Index: 1363482 (Open Web Text)

Max Activating Token Index: 871

Text #2

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.1921. Min Act: -0.1700

Data Index: 8489928 (Open Web Text)

Max Activating Token Index: 746

Text #3

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.1643. Min Act: -0.1700

Data Index: 6306974 (Open Web Text)

Max Activating Token Index: 944

Text #4

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.0741. Min Act: -0.1700

Data Index: 1242983 (Open Web Text)

Max Activating Token Index: 147

Text #5

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.0436. Min Act: -0.1700

Data Index: 819162 (Open Web Text)

Max Activating Token Index: 781

Text #6

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.0256. Min Act: -0.1700

Data Index: 670031 (Open Web Text)

Max Activating Token Index: 641

Text #7

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.0472. Min Act: -0.1700

Data Index: 4224367 (Open Web Text)

Max Activating Token Index: 403

Text #8

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.9926. Min Act: -0.1700

Data Index: 7207706 (Open Web Text)

Max Activating Token Index: 669

Text #9

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.9748. Min Act: -0.1700

Data Index: 1156365 (Open Web Text)

Max Activating Token Index: 75

Text #10

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.9408. Min Act: -0.1700

Data Index: 7402611 (Open Web Text)

Max Activating Token Index: 443

Text #11

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.9442. Min Act: -0.1700

Data Index: 7693869 (Open Web Text)

Max Activating Token Index: 910

Text #12

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.9387. Min Act: -0.1700

Data Index: 2788666 (Open Web Text)

Max Activating Token Index: 616

Text #13

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.9150. Min Act: -0.1700

Data Index: 738208 (Open Web Text)

Max Activating Token Index: 993

Text #14

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.9220. Min Act: -0.1700

Data Index: 682433 (Open Web Text)

Max Activating Token Index: 260

Text #15

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.9418. Min Act: -0.1700

Data Index: 342167 (Open Web Text)

Max Activating Token Index: 104

Text #16

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.9112. Min Act: -0.1700

Data Index: 4766392 (Open Web Text)

Max Activating Token Index: 141

Text #17

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.9364. Min Act: -0.1700

Data Index: 3198688 (Open Web Text)

Max Activating Token Index: 857

Text #18

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.9278. Min Act: -0.1700

Data Index: 1692648 (Open Web Text)

Max Activating Token Index: 535

Text #19

Max Range: 3.2558. Min Range: -3.2558

Max Act: 2.9205. Min Act: -0.1700

Data Index: 1165708 (Open Web Text)

Max Activating Token Index: 130