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

Dataset: Open Web Text

Neuron 1473 in Layer 5

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: 4.8192. Min Range: -4.8192

Max Act: 4.8192. Min Act: -0.1700

Data Index: 8538941 (Open Web Text)

Max Activating Token Index: 895

Text #1

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.7042. Min Act: -0.1700

Data Index: 8307743 (Open Web Text)

Max Activating Token Index: 978

Text #2

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.7041. Min Act: -0.1700

Data Index: 3921615 (Open Web Text)

Max Activating Token Index: 675

Text #3

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.6384. Min Act: -0.1700

Data Index: 5242614 (Open Web Text)

Max Activating Token Index: 905

Text #4

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.6735. Min Act: -0.1700

Data Index: 8154682 (Open Web Text)

Max Activating Token Index: 57

Text #5

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.6164. Min Act: -0.1700

Data Index: 5027917 (Open Web Text)

Max Activating Token Index: 629

Text #6

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.6481. Min Act: -0.1700

Data Index: 1161198 (Open Web Text)

Max Activating Token Index: 1012

Text #7

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.6021. Min Act: -0.1700

Data Index: 8376250 (Open Web Text)

Max Activating Token Index: 707

Text #8

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.5982. Min Act: -0.1700

Data Index: 2610974 (Open Web Text)

Max Activating Token Index: 798

Text #9

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.5751. Min Act: -0.1700

Data Index: 2760148 (Open Web Text)

Max Activating Token Index: 403

Text #10

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.6116. Min Act: -0.1700

Data Index: 2133536 (Open Web Text)

Max Activating Token Index: 584

Text #11

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.5525. Min Act: -0.1700

Data Index: 921732 (Open Web Text)

Max Activating Token Index: 645

Text #12

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.5529. Min Act: -0.1700

Data Index: 2405495 (Open Web Text)

Max Activating Token Index: 338

Text #13

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.5711. Min Act: -0.1700

Data Index: 6152382 (Open Web Text)

Max Activating Token Index: 581

Text #14

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.5718. Min Act: -0.1700

Data Index: 1194238 (Open Web Text)

Max Activating Token Index: 638

Text #15

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.5861. Min Act: -0.1700

Data Index: 7893954 (Open Web Text)

Max Activating Token Index: 758

Text #16

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.5603. Min Act: -0.1700

Data Index: 7758628 (Open Web Text)

Max Activating Token Index: 959

Text #17

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.5808. Min Act: -0.1700

Data Index: 7696045 (Open Web Text)

Max Activating Token Index: 824

Text #18

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.5902. Min Act: -0.1700

Data Index: 4996552 (Open Web Text)

Max Activating Token Index: 377

Text #19

Max Range: 4.8192. Min Range: -4.8192

Max Act: 4.5843. Min Act: -0.1700

Data Index: 2526749 (Open Web Text)

Max Activating Token Index: 882