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

Dataset: Open Web Text

Neuron 2642 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: 5.0835. Min Range: -5.0835

Max Act: 5.0835. Min Act: -0.1700

Data Index: 8455166 (Open Web Text)

Max Activating Token Index: 765

Text #1

Max Range: 5.0835. Min Range: -5.0835

Max Act: 5.0689. Min Act: -0.1700

Data Index: 7548866 (Open Web Text)

Max Activating Token Index: 946

Text #2

Max Range: 5.0835. Min Range: -5.0835

Max Act: 5.0373. Min Act: -0.1700

Data Index: 8073760 (Open Web Text)

Max Activating Token Index: 396

Text #3

Max Range: 5.0835. Min Range: -5.0835

Max Act: 5.0540. Min Act: -0.1700

Data Index: 7688705 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 5.0835. Min Range: -5.0835

Max Act: 5.0005. Min Act: -0.1700

Data Index: 4755540 (Open Web Text)

Max Activating Token Index: 903

Text #5

Max Range: 5.0835. Min Range: -5.0835

Max Act: 5.0103. Min Act: -0.1700

Data Index: 716357 (Open Web Text)

Max Activating Token Index: 635

Text #6

Max Range: 5.0835. Min Range: -5.0835

Max Act: 5.0168. Min Act: -0.1700

Data Index: 1351489 (Open Web Text)

Max Activating Token Index: 492

Text #7

Max Range: 5.0835. Min Range: -5.0835

Max Act: 5.0199. Min Act: -0.1700

Data Index: 7914938 (Open Web Text)

Max Activating Token Index: 601

Text #8

Max Range: 5.0835. Min Range: -5.0835

Max Act: 4.9761. Min Act: -0.1700

Data Index: 7449025 (Open Web Text)

Max Activating Token Index: 697

Text #9

Max Range: 5.0835. Min Range: -5.0835

Max Act: 4.9946. Min Act: -0.1700

Data Index: 1772511 (Open Web Text)

Max Activating Token Index: 468

Text #10

Max Range: 5.0835. Min Range: -5.0835

Max Act: 4.9621. Min Act: -0.1700

Data Index: 1996331 (Open Web Text)

Max Activating Token Index: 110

Text #11

Max Range: 5.0835. Min Range: -5.0835

Max Act: 4.9525. Min Act: -0.1700

Data Index: 4946501 (Open Web Text)

Max Activating Token Index: 1013

Text #12

Max Range: 5.0835. Min Range: -5.0835

Max Act: 4.9777. Min Act: -0.1700

Data Index: 5128460 (Open Web Text)

Max Activating Token Index: 383

Text #13

Max Range: 5.0835. Min Range: -5.0835

Max Act: 4.9339. Min Act: -0.1700

Data Index: 5030548 (Open Web Text)

Max Activating Token Index: 808

Text #14

Max Range: 5.0835. Min Range: -5.0835

Max Act: 4.8998. Min Act: -0.1700

Data Index: 6586005 (Open Web Text)

Max Activating Token Index: 643

Text #15

Max Range: 5.0835. Min Range: -5.0835

Max Act: 4.9409. Min Act: -0.1700

Data Index: 2619351 (Open Web Text)

Max Activating Token Index: 330

Text #16

Max Range: 5.0835. Min Range: -5.0835

Max Act: 4.8859. Min Act: -0.1700

Data Index: 4955890 (Open Web Text)

Max Activating Token Index: 810

Text #17

Max Range: 5.0835. Min Range: -5.0835

Max Act: 4.8673. Min Act: -0.1700

Data Index: 8723002 (Open Web Text)

Max Activating Token Index: 870

Text #18

Max Range: 5.0835. Min Range: -5.0835

Max Act: 4.8786. Min Act: -0.1700

Data Index: 8237240 (Open Web Text)

Max Activating Token Index: 474

Text #19

Max Range: 5.0835. Min Range: -5.0835

Max Act: 4.8774. Min Act: -0.1700

Data Index: 4695556 (Open Web Text)

Max Activating Token Index: 375