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

Dataset: Open Web Text

Neuron 797 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: 5.1437. Min Range: -5.1437

Max Act: 5.1437. Min Act: -0.1700

Data Index: 4956309 (Open Web Text)

Max Activating Token Index: 317

Text #1

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.9812. Min Act: -0.1700

Data Index: 2212629 (Open Web Text)

Max Activating Token Index: 138

Text #2

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.9421. Min Act: -0.1700

Data Index: 5177468 (Open Web Text)

Max Activating Token Index: 518

Text #3

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.9058. Min Act: -0.1700

Data Index: 402980 (Open Web Text)

Max Activating Token Index: 620

Text #4

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.9615. Min Act: -0.1700

Data Index: 5108168 (Open Web Text)

Max Activating Token Index: 508

Text #5

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.9151. Min Act: -0.1700

Data Index: 3547424 (Open Web Text)

Max Activating Token Index: 273

Text #6

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.8685. Min Act: -0.1700

Data Index: 6364207 (Open Web Text)

Max Activating Token Index: 756

Text #7

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.8661. Min Act: -0.1700

Data Index: 4095624 (Open Web Text)

Max Activating Token Index: 726

Text #8

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.8670. Min Act: -0.1700

Data Index: 2387576 (Open Web Text)

Max Activating Token Index: 936

Text #9

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.8940. Min Act: -0.1700

Data Index: 538562 (Open Web Text)

Max Activating Token Index: 388

Text #10

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.8914. Min Act: -0.1700

Data Index: 3555804 (Open Web Text)

Max Activating Token Index: 336

Text #11

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.8443. Min Act: -0.1700

Data Index: 6405381 (Open Web Text)

Max Activating Token Index: 112

Text #12

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.8443. Min Act: -0.1700

Data Index: 4020054 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.8405. Min Act: -0.1700

Data Index: 5683154 (Open Web Text)

Max Activating Token Index: 418

Text #14

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.8312. Min Act: -0.1700

Data Index: 820140 (Open Web Text)

Max Activating Token Index: 309

Text #15

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.8411. Min Act: -0.1700

Data Index: 8001029 (Open Web Text)

Max Activating Token Index: 953

Text #16

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.7491. Min Act: -0.1700

Data Index: 1351375 (Open Web Text)

Max Activating Token Index: 512

Text #17

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.8025. Min Act: -0.1700

Data Index: 2127100 (Open Web Text)

Max Activating Token Index: 228

Text #18

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.8203. Min Act: -0.1700

Data Index: 4102067 (Open Web Text)

Max Activating Token Index: 746

Text #19

Max Range: 5.1437. Min Range: -5.1437

Max Act: 4.8125. Min Act: -0.1700

Data Index: 4930959 (Open Web Text)

Max Activating Token Index: 861