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

Dataset: Open Web Text

Neuron 2475 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: 3.0016. Min Range: -3.0016

Max Act: 3.0016. Min Act: -0.1700

Data Index: 8775819 (Open Web Text)

Max Activating Token Index: 617

Text #1

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8711. Min Act: -0.1700

Data Index: 6906232 (Open Web Text)

Max Activating Token Index: 315

Text #2

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8469. Min Act: -0.1700

Data Index: 6138691 (Open Web Text)

Max Activating Token Index: 615

Text #3

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8246. Min Act: -0.1700

Data Index: 90107 (Open Web Text)

Max Activating Token Index: 695

Text #4

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8369. Min Act: -0.1700

Data Index: 1581550 (Open Web Text)

Max Activating Token Index: 605

Text #5

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8058. Min Act: -0.1700

Data Index: 811847 (Open Web Text)

Max Activating Token Index: 708

Text #6

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8242. Min Act: -0.1700

Data Index: 1349881 (Open Web Text)

Max Activating Token Index: 589

Text #7

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7910. Min Act: -0.1700

Data Index: 3298416 (Open Web Text)

Max Activating Token Index: 829

Text #8

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7970. Min Act: -0.1700

Data Index: 3769114 (Open Web Text)

Max Activating Token Index: 777

Text #9

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7595. Min Act: -0.1700

Data Index: 5166794 (Open Web Text)

Max Activating Token Index: 331

Text #10

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7683. Min Act: -0.1700

Data Index: 4436014 (Open Web Text)

Max Activating Token Index: 158

Text #11

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7669. Min Act: -0.1700

Data Index: 2558531 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7772. Min Act: -0.1700

Data Index: 5625534 (Open Web Text)

Max Activating Token Index: 780

Text #13

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7475. Min Act: -0.1700

Data Index: 1974190 (Open Web Text)

Max Activating Token Index: 770

Text #14

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7436. Min Act: -0.1700

Data Index: 2551584 (Open Web Text)

Max Activating Token Index: 456

Text #15

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7295. Min Act: -0.1700

Data Index: 7787390 (Open Web Text)

Max Activating Token Index: 449

Text #16

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7439. Min Act: -0.1700

Data Index: 8792840 (Open Web Text)

Max Activating Token Index: 132

Text #17

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7220. Min Act: -0.1700

Data Index: 6504312 (Open Web Text)

Max Activating Token Index: 466

Text #18

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7253. Min Act: -0.1700

Data Index: 5453614 (Open Web Text)

Max Activating Token Index: 349

Text #19

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7355. Min Act: -0.1700

Data Index: 8389413 (Open Web Text)

Max Activating Token Index: 735