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

Dataset: Open Web Text

Neuron 349 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: 5.0543. Min Range: -5.0543

Max Act: 5.0543. Min Act: -0.1700

Data Index: 6738691 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.8829. Min Act: -0.1700

Data Index: 5485046 (Open Web Text)

Max Activating Token Index: 461

Text #2

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.7608. Min Act: -0.1700

Data Index: 1035097 (Open Web Text)

Max Activating Token Index: 996

Text #3

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.7932. Min Act: -0.1700

Data Index: 7933814 (Open Web Text)

Max Activating Token Index: 289

Text #4

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.6965. Min Act: -0.1700

Data Index: 3831799 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.6655. Min Act: -0.1700

Data Index: 7689162 (Open Web Text)

Max Activating Token Index: 1004

Text #6

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.6792. Min Act: -0.1700

Data Index: 2823251 (Open Web Text)

Max Activating Token Index: 1020

Text #7

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.7008. Min Act: -0.1700

Data Index: 1480982 (Open Web Text)

Max Activating Token Index: 762

Text #8

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.6517. Min Act: -0.1700

Data Index: 8216574 (Open Web Text)

Max Activating Token Index: 596

Text #9

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.6065. Min Act: -0.1700

Data Index: 7056955 (Open Web Text)

Max Activating Token Index: 536

Text #10

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.5552. Min Act: -0.1700

Data Index: 885649 (Open Web Text)

Max Activating Token Index: 911

Text #11

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.5834. Min Act: -0.1700

Data Index: 6016042 (Open Web Text)

Max Activating Token Index: 103

Text #12

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.5854. Min Act: -0.1700

Data Index: 2294097 (Open Web Text)

Max Activating Token Index: 548

Text #13

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.5772. Min Act: -0.1700

Data Index: 5015537 (Open Web Text)

Max Activating Token Index: 223

Text #14

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.5385. Min Act: -0.1700

Data Index: 655131 (Open Web Text)

Max Activating Token Index: 832

Text #15

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.5603. Min Act: -0.1700

Data Index: 2182731 (Open Web Text)

Max Activating Token Index: 540

Text #16

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.5463. Min Act: -0.1700

Data Index: 7830236 (Open Web Text)

Max Activating Token Index: 827

Text #17

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.5650. Min Act: -0.1700

Data Index: 3911380 (Open Web Text)

Max Activating Token Index: 500

Text #18

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.5141. Min Act: -0.1700

Data Index: 381565 (Open Web Text)

Max Activating Token Index: 53

Text #19

Max Range: 5.0543. Min Range: -5.0543

Max Act: 4.5477. Min Act: -0.1700

Data Index: 7288758 (Open Web Text)

Max Activating Token Index: 1011