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

Dataset: Open Web Text

Neuron 19 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: 4.2558. Min Range: -4.2558

Max Act: 4.2558. Min Act: -0.1700

Data Index: 4904386 (Open Web Text)

Max Activating Token Index: 799

Text #1

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.2449. Min Act: -0.1700

Data Index: 566650 (Open Web Text)

Max Activating Token Index: 978

Text #2

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1957. Min Act: -0.1700

Data Index: 8248609 (Open Web Text)

Max Activating Token Index: 530

Text #3

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1683. Min Act: -0.1700

Data Index: 2714794 (Open Web Text)

Max Activating Token Index: 233

Text #4

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1336. Min Act: -0.1700

Data Index: 1883767 (Open Web Text)

Max Activating Token Index: 601

Text #5

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1335. Min Act: -0.1700

Data Index: 6550220 (Open Web Text)

Max Activating Token Index: 987

Text #6

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1627. Min Act: -0.1700

Data Index: 7452190 (Open Web Text)

Max Activating Token Index: 82

Text #7

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1295. Min Act: -0.1700

Data Index: 4614825 (Open Web Text)

Max Activating Token Index: 339

Text #8

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1112. Min Act: -0.1700

Data Index: 7598281 (Open Web Text)

Max Activating Token Index: 333

Text #9

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1096. Min Act: -0.1700

Data Index: 301516 (Open Web Text)

Max Activating Token Index: 906

Text #10

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1089. Min Act: -0.1700

Data Index: 4361272 (Open Web Text)

Max Activating Token Index: 551

Text #11

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.0866. Min Act: -0.1700

Data Index: 2901968 (Open Web Text)

Max Activating Token Index: 727

Text #12

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1020. Min Act: -0.1700

Data Index: 180217 (Open Web Text)

Max Activating Token Index: 476

Text #13

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.0650. Min Act: -0.1700

Data Index: 2555510 (Open Web Text)

Max Activating Token Index: 84

Text #14

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.0483. Min Act: -0.1700

Data Index: 7282751 (Open Web Text)

Max Activating Token Index: 406

Text #15

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.0653. Min Act: -0.1700

Data Index: 8435988 (Open Web Text)

Max Activating Token Index: 929

Text #16

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.0662. Min Act: -0.1700

Data Index: 7267813 (Open Web Text)

Max Activating Token Index: 1001

Text #17

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.9802. Min Act: -0.1700

Data Index: 5033580 (Open Web Text)

Max Activating Token Index: 476

Text #18

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.9941. Min Act: -0.1700

Data Index: 2870821 (Open Web Text)

Max Activating Token Index: 973

Text #19

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.9670. Min Act: -0.1700

Data Index: 1290718 (Open Web Text)

Max Activating Token Index: 292