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

Dataset: Open Web Text

Neuron 2746 in Layer 3

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: 4.1242. Min Range: -4.1242

Max Act: 4.1242. Min Act: -0.1700

Data Index: 3033009 (Open Web Text)

Max Activating Token Index: 445

Text #1

Max Range: 4.1242. Min Range: -4.1242

Max Act: 4.0327. Min Act: -0.1700

Data Index: 5690259 (Open Web Text)

Max Activating Token Index: 252

Text #2

Max Range: 4.1242. Min Range: -4.1242

Max Act: 4.0410. Min Act: -0.1700

Data Index: 524625 (Open Web Text)

Max Activating Token Index: 403

Text #3

Max Range: 4.1242. Min Range: -4.1242

Max Act: 4.0384. Min Act: -0.1700

Data Index: 1545549 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.9988. Min Act: -0.1700

Data Index: 8197115 (Open Web Text)

Max Activating Token Index: 144

Text #5

Max Range: 4.1242. Min Range: -4.1242

Max Act: 4.0015. Min Act: -0.1700

Data Index: 390246 (Open Web Text)

Max Activating Token Index: 122

Text #6

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.9346. Min Act: -0.1700

Data Index: 6098753 (Open Web Text)

Max Activating Token Index: 299

Text #7

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.9618. Min Act: -0.1700

Data Index: 119009 (Open Web Text)

Max Activating Token Index: 418

Text #8

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.9437. Min Act: -0.1700

Data Index: 8193599 (Open Web Text)

Max Activating Token Index: 419

Text #9

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.9728. Min Act: -0.1700

Data Index: 385047 (Open Web Text)

Max Activating Token Index: 390

Text #10

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.9301. Min Act: -0.1700

Data Index: 7689077 (Open Web Text)

Max Activating Token Index: 754

Text #11

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.9836. Min Act: -0.1700

Data Index: 605397 (Open Web Text)

Max Activating Token Index: 541

Text #12

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.9715. Min Act: -0.1700

Data Index: 4093640 (Open Web Text)

Max Activating Token Index: 375

Text #13

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.8971. Min Act: -0.1700

Data Index: 8362651 (Open Web Text)

Max Activating Token Index: 458

Text #14

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.9132. Min Act: -0.1700

Data Index: 2787482 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.9123. Min Act: -0.1700

Data Index: 4472287 (Open Web Text)

Max Activating Token Index: 395

Text #16

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.9004. Min Act: -0.1700

Data Index: 6909891 (Open Web Text)

Max Activating Token Index: 80

Text #17

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.9361. Min Act: -0.1700

Data Index: 1658513 (Open Web Text)

Max Activating Token Index: 969

Text #18

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.8954. Min Act: -0.1700

Data Index: 4613015 (Open Web Text)

Max Activating Token Index: 436

Text #19

Max Range: 4.1242. Min Range: -4.1242

Max Act: 3.8812. Min Act: -0.1700

Data Index: 7725709 (Open Web Text)

Max Activating Token Index: 124