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

Dataset: Open Web Text

Neuron 1198 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: 6.3175. Min Range: -6.3175

Max Act: 6.3175. Min Act: -0.1700

Data Index: 4516903 (Open Web Text)

Max Activating Token Index: 96

Text #1

Max Range: 6.3175. Min Range: -6.3175

Max Act: 6.2435. Min Act: -0.1700

Data Index: 5975983 (Open Web Text)

Max Activating Token Index: 503

Text #2

Max Range: 6.3175. Min Range: -6.3175

Max Act: 6.0726. Min Act: -0.1700

Data Index: 2736320 (Open Web Text)

Max Activating Token Index: 530

Text #3

Max Range: 6.3175. Min Range: -6.3175

Max Act: 6.0772. Min Act: -0.1700

Data Index: 7653633 (Open Web Text)

Max Activating Token Index: 216

Text #4

Max Range: 6.3175. Min Range: -6.3175

Max Act: 6.0870. Min Act: -0.1700

Data Index: 2806396 (Open Web Text)

Max Activating Token Index: 322

Text #5

Max Range: 6.3175. Min Range: -6.3175

Max Act: 6.0629. Min Act: -0.1700

Data Index: 629088 (Open Web Text)

Max Activating Token Index: 844

Text #6

Max Range: 6.3175. Min Range: -6.3175

Max Act: 6.0269. Min Act: -0.1700

Data Index: 2595097 (Open Web Text)

Max Activating Token Index: 367

Text #7

Max Range: 6.3175. Min Range: -6.3175

Max Act: 6.0404. Min Act: -0.1700

Data Index: 6864096 (Open Web Text)

Max Activating Token Index: 57

Text #8

Max Range: 6.3175. Min Range: -6.3175

Max Act: 6.0512. Min Act: -0.1700

Data Index: 7441227 (Open Web Text)

Max Activating Token Index: 268

Text #9

Max Range: 6.3175. Min Range: -6.3175

Max Act: 6.0022. Min Act: -0.1700

Data Index: 7600248 (Open Web Text)

Max Activating Token Index: 864

Text #10

Max Range: 6.3175. Min Range: -6.3175

Max Act: 5.9964. Min Act: -0.1700

Data Index: 4800970 (Open Web Text)

Max Activating Token Index: 416

Text #11

Max Range: 6.3175. Min Range: -6.3175

Max Act: 5.9976. Min Act: -0.1700

Data Index: 4348200 (Open Web Text)

Max Activating Token Index: 371

Text #12

Max Range: 6.3175. Min Range: -6.3175

Max Act: 5.9957. Min Act: -0.1700

Data Index: 8067861 (Open Web Text)

Max Activating Token Index: 304

Text #13

Max Range: 6.3175. Min Range: -6.3175

Max Act: 6.0095. Min Act: -0.1700

Data Index: 2257557 (Open Web Text)

Max Activating Token Index: 710

Text #14

Max Range: 6.3175. Min Range: -6.3175

Max Act: 5.9335. Min Act: -0.1700

Data Index: 7729823 (Open Web Text)

Max Activating Token Index: 952

Text #15

Max Range: 6.3175. Min Range: -6.3175

Max Act: 5.9397. Min Act: -0.1700

Data Index: 1511452 (Open Web Text)

Max Activating Token Index: 686

Text #16

Max Range: 6.3175. Min Range: -6.3175

Max Act: 5.9755. Min Act: -0.1700

Data Index: 6391873 (Open Web Text)

Max Activating Token Index: 636

Text #17

Max Range: 6.3175. Min Range: -6.3175

Max Act: 5.9627. Min Act: -0.1700

Data Index: 1237437 (Open Web Text)

Max Activating Token Index: 809

Text #18

Max Range: 6.3175. Min Range: -6.3175

Max Act: 5.9666. Min Act: -0.1700

Data Index: 3534568 (Open Web Text)

Max Activating Token Index: 715

Text #19

Max Range: 6.3175. Min Range: -6.3175

Max Act: 5.9815. Min Act: -0.1700

Data Index: 7360395 (Open Web Text)

Max Activating Token Index: 475