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

Dataset: Open Web Text

Neuron 1694 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: 4.0315. Min Range: -4.0315

Max Act: 4.0315. Min Act: -0.1700

Data Index: 6010084 (Open Web Text)

Max Activating Token Index: 778

Text #1

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.9941. Min Act: -0.1700

Data Index: 5642730 (Open Web Text)

Max Activating Token Index: 250

Text #2

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.9923. Min Act: -0.1700

Data Index: 7882107 (Open Web Text)

Max Activating Token Index: 508

Text #3

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.9702. Min Act: -0.1700

Data Index: 4287382 (Open Web Text)

Max Activating Token Index: 53

Text #4

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.9401. Min Act: -0.1700

Data Index: 66649 (Open Web Text)

Max Activating Token Index: 963

Text #5

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.9179. Min Act: -0.1700

Data Index: 1870101 (Open Web Text)

Max Activating Token Index: 453

Text #6

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.9338. Min Act: -0.1700

Data Index: 1896847 (Open Web Text)

Max Activating Token Index: 174

Text #7

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.9430. Min Act: -0.1700

Data Index: 1825566 (Open Web Text)

Max Activating Token Index: 284

Text #8

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.8947. Min Act: -0.1700

Data Index: 5727715 (Open Web Text)

Max Activating Token Index: 598

Text #9

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.8882. Min Act: -0.1700

Data Index: 3890349 (Open Web Text)

Max Activating Token Index: 969

Text #10

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.8843. Min Act: -0.1700

Data Index: 6324215 (Open Web Text)

Max Activating Token Index: 202

Text #11

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.8907. Min Act: -0.1700

Data Index: 3582549 (Open Web Text)

Max Activating Token Index: 441

Text #12

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.8804. Min Act: -0.1700

Data Index: 4782900 (Open Web Text)

Max Activating Token Index: 925

Text #13

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.8754. Min Act: -0.1700

Data Index: 3025946 (Open Web Text)

Max Activating Token Index: 242

Text #14

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.9077. Min Act: -0.1700

Data Index: 1749605 (Open Web Text)

Max Activating Token Index: 773

Text #15

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.8663. Min Act: -0.1700

Data Index: 2347368 (Open Web Text)

Max Activating Token Index: 34

Text #16

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.8701. Min Act: -0.1700

Data Index: 1412398 (Open Web Text)

Max Activating Token Index: 648

Text #17

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.8616. Min Act: -0.1700

Data Index: 4599905 (Open Web Text)

Max Activating Token Index: 311

Text #18

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.8790. Min Act: -0.1700

Data Index: 3965694 (Open Web Text)

Max Activating Token Index: 1005

Text #19

Max Range: 4.0315. Min Range: -4.0315

Max Act: 3.8654. Min Act: -0.1700

Data Index: 1127242 (Open Web Text)

Max Activating Token Index: 78