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

Dataset: Open Web Text

Neuron 1908 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: 4.2308. Min Range: -4.2308

Max Act: 4.2308. Min Act: -0.1700

Data Index: 6889219 (Open Web Text)

Max Activating Token Index: 85

Text #1

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.1388. Min Act: -0.1700

Data Index: 5725377 (Open Web Text)

Max Activating Token Index: 268

Text #2

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.1394. Min Act: -0.1700

Data Index: 4949860 (Open Web Text)

Max Activating Token Index: 733

Text #3

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.1626. Min Act: -0.1700

Data Index: 2089559 (Open Web Text)

Max Activating Token Index: 1006

Text #4

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.1085. Min Act: -0.1700

Data Index: 1260566 (Open Web Text)

Max Activating Token Index: 103

Text #5

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.1339. Min Act: -0.1700

Data Index: 8159705 (Open Web Text)

Max Activating Token Index: 429

Text #6

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.0997. Min Act: -0.1700

Data Index: 8247246 (Open Web Text)

Max Activating Token Index: 700

Text #7

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.0838. Min Act: -0.1700

Data Index: 5323951 (Open Web Text)

Max Activating Token Index: 741

Text #8

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.0657. Min Act: -0.1700

Data Index: 2576038 (Open Web Text)

Max Activating Token Index: 83

Text #9

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.0750. Min Act: -0.1700

Data Index: 6682948 (Open Web Text)

Max Activating Token Index: 684

Text #10

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.0232. Min Act: -0.1700

Data Index: 3780488 (Open Web Text)

Max Activating Token Index: 823

Text #11

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9917. Min Act: -0.1700

Data Index: 5097925 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9728. Min Act: -0.1700

Data Index: 2506034 (Open Web Text)

Max Activating Token Index: 755

Text #13

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9471. Min Act: -0.1700

Data Index: 7890386 (Open Web Text)

Max Activating Token Index: 812

Text #14

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9601. Min Act: -0.1700

Data Index: 6318345 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9579. Min Act: -0.1700

Data Index: 3618807 (Open Web Text)

Max Activating Token Index: 565

Text #16

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9180. Min Act: -0.1700

Data Index: 2178017 (Open Web Text)

Max Activating Token Index: 772

Text #17

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9464. Min Act: -0.1700

Data Index: 3438061 (Open Web Text)

Max Activating Token Index: 419

Text #18

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9493. Min Act: -0.1700

Data Index: 2250200 (Open Web Text)

Max Activating Token Index: 610

Text #19

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9481. Min Act: -0.1700

Data Index: 1101798 (Open Web Text)

Max Activating Token Index: 471