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

Dataset: Open Web Text

Neuron 990 in Layer 2

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: 4.9742. Min Range: -4.9742

Max Act: 4.9742. Min Act: -0.1700

Data Index: 4834426 (Open Web Text)

Max Activating Token Index: 382

Text #1

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.9439. Min Act: -0.1700

Data Index: 6366408 (Open Web Text)

Max Activating Token Index: 567

Text #2

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.8991. Min Act: -0.1700

Data Index: 2513056 (Open Web Text)

Max Activating Token Index: 705

Text #3

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.8927. Min Act: -0.1700

Data Index: 8253803 (Open Web Text)

Max Activating Token Index: 199

Text #4

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.8751. Min Act: -0.1700

Data Index: 6113619 (Open Web Text)

Max Activating Token Index: 411

Text #5

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.8181. Min Act: -0.1700

Data Index: 3421106 (Open Web Text)

Max Activating Token Index: 458

Text #6

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.8116. Min Act: -0.1700

Data Index: 6726258 (Open Web Text)

Max Activating Token Index: 175

Text #7

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.7836. Min Act: -0.1700

Data Index: 3936270 (Open Web Text)

Max Activating Token Index: 708

Text #8

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.7906. Min Act: -0.1700

Data Index: 6309005 (Open Web Text)

Max Activating Token Index: 367

Text #9

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.7754. Min Act: -0.1700

Data Index: 6310439 (Open Web Text)

Max Activating Token Index: 55

Text #10

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.7696. Min Act: -0.1700

Data Index: 2882478 (Open Web Text)

Max Activating Token Index: 150

Text #11

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.7718. Min Act: -0.1700

Data Index: 8457195 (Open Web Text)

Max Activating Token Index: 608

Text #12

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.7319. Min Act: -0.1700

Data Index: 7155372 (Open Web Text)

Max Activating Token Index: 367

Text #13

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.7441. Min Act: -0.1700

Data Index: 19159 (Open Web Text)

Max Activating Token Index: 936

Text #14

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.7472. Min Act: -0.1700

Data Index: 8683189 (Open Web Text)

Max Activating Token Index: 279

Text #15

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.7456. Min Act: -0.1700

Data Index: 1340892 (Open Web Text)

Max Activating Token Index: 579

Text #16

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.7682. Min Act: -0.1700

Data Index: 4440272 (Open Web Text)

Max Activating Token Index: 234

Text #17

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.7519. Min Act: -0.1700

Data Index: 2694459 (Open Web Text)

Max Activating Token Index: 346

Text #18

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.7838. Min Act: -0.1700

Data Index: 1481170 (Open Web Text)

Max Activating Token Index: 857

Text #19

Max Range: 4.9742. Min Range: -4.9742

Max Act: 4.7687. Min Act: -0.1700

Data Index: 893174 (Open Web Text)

Max Activating Token Index: 367