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

Dataset: Open Web Text

Neuron 3000 in Layer 1

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: 1.4004. Min Range: -1.4004

Max Act: 1.4004. Min Act: -0.1700

Data Index: 7712614 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3782. Min Act: -0.1700

Data Index: 7936015 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3676. Min Act: -0.1699

Data Index: 6531653 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3555. Min Act: -0.1700

Data Index: 655082 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3439. Min Act: -0.1700

Data Index: 4925633 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3486. Min Act: -0.1700

Data Index: 8424358 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3486. Min Act: -0.1700

Data Index: 8743330 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3402. Min Act: -0.1700

Data Index: 5417773 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3402. Min Act: -0.1700

Data Index: 5949353 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3243. Min Act: -0.1700

Data Index: 1575056 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3197. Min Act: -0.1700

Data Index: 4384703 (Open Web Text)

Max Activating Token Index: 117

Text #11

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3207. Min Act: -0.1700

Data Index: 5041530 (Open Web Text)

Max Activating Token Index: 26

Text #12

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3057. Min Act: -0.1700

Data Index: 8149595 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3149. Min Act: -0.1700

Data Index: 4076707 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3092. Min Act: -0.1700

Data Index: 3150405 (Open Web Text)

Max Activating Token Index: 32

Text #15

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3189. Min Act: -0.1700

Data Index: 3000426 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.2996. Min Act: -0.1700

Data Index: 2039200 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3078. Min Act: -0.1700

Data Index: 4384701 (Open Web Text)

Max Activating Token Index: 401

Text #18

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3019. Min Act: -0.1700

Data Index: 3590997 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.3038. Min Act: -0.1700

Data Index: 707339 (Open Web Text)

Max Activating Token Index: 7