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

Dataset: Open Web Text

Neuron 869 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: 4.1280. Min Range: -4.1280

Max Act: 4.1280. Min Act: -0.1700

Data Index: 1067636 (Open Web Text)

Max Activating Token Index: 719

Text #1

Max Range: 4.1280. Min Range: -4.1280

Max Act: 4.0967. Min Act: -0.1700

Data Index: 985690 (Open Web Text)

Max Activating Token Index: 620

Text #2

Max Range: 4.1280. Min Range: -4.1280

Max Act: 4.0732. Min Act: -0.1700

Data Index: 8321603 (Open Web Text)

Max Activating Token Index: 679

Text #3

Max Range: 4.1280. Min Range: -4.1280

Max Act: 4.0338. Min Act: -0.1700

Data Index: 5216534 (Open Web Text)

Max Activating Token Index: 661

Text #4

Max Range: 4.1280. Min Range: -4.1280

Max Act: 4.0065. Min Act: -0.1700

Data Index: 3949193 (Open Web Text)

Max Activating Token Index: 115

Text #5

Max Range: 4.1280. Min Range: -4.1280

Max Act: 4.0242. Min Act: -0.1700

Data Index: 3939054 (Open Web Text)

Max Activating Token Index: 609

Text #6

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9719. Min Act: -0.1700

Data Index: 8061526 (Open Web Text)

Max Activating Token Index: 613

Text #7

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9687. Min Act: -0.1700

Data Index: 7069791 (Open Web Text)

Max Activating Token Index: 1009

Text #8

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9755. Min Act: -0.1700

Data Index: 5657364 (Open Web Text)

Max Activating Token Index: 361

Text #9

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9641. Min Act: -0.1700

Data Index: 7937876 (Open Web Text)

Max Activating Token Index: 81

Text #10

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9894. Min Act: -0.1700

Data Index: 7404419 (Open Web Text)

Max Activating Token Index: 527

Text #11

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9587. Min Act: -0.1700

Data Index: 111011 (Open Web Text)

Max Activating Token Index: 508

Text #12

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9337. Min Act: -0.1700

Data Index: 5094215 (Open Web Text)

Max Activating Token Index: 316

Text #13

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9515. Min Act: -0.1700

Data Index: 2012512 (Open Web Text)

Max Activating Token Index: 700

Text #14

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9635. Min Act: -0.1700

Data Index: 1455421 (Open Web Text)

Max Activating Token Index: 274

Text #15

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9321. Min Act: -0.1700

Data Index: 4860865 (Open Web Text)

Max Activating Token Index: 887

Text #16

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9353. Min Act: -0.1700

Data Index: 5398090 (Open Web Text)

Max Activating Token Index: 736

Text #17

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9199. Min Act: -0.1700

Data Index: 1627553 (Open Web Text)

Max Activating Token Index: 244

Text #18

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9413. Min Act: -0.1700

Data Index: 1466205 (Open Web Text)

Max Activating Token Index: 928

Text #19

Max Range: 4.1280. Min Range: -4.1280

Max Act: 3.9507. Min Act: -0.1700

Data Index: 6641824 (Open Web Text)

Max Activating Token Index: 478