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

Dataset: Open Web Text

Neuron 1479 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: 1.6149. Min Range: -1.6149

Max Act: 1.6149. Min Act: -0.1700

Data Index: 5242384 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.5704. Min Act: -0.1700

Data Index: 8292115 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.5596. Min Act: -0.1700

Data Index: 8769941 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.5635. Min Act: -0.1700

Data Index: 4341032 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.5494. Min Act: -0.1700

Data Index: 1177077 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.5378. Min Act: -0.1700

Data Index: 1488596 (Open Web Text)

Max Activating Token Index: 24

Text #6

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.5382. Min Act: -0.1697

Data Index: 7825247 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.5264. Min Act: -0.1700

Data Index: 5187157 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.5297. Min Act: -0.1700

Data Index: 2374714 (Open Web Text)

Max Activating Token Index: 1021

Text #9

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.5193. Min Act: -0.1699

Data Index: 4045187 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.5142. Min Act: -0.1700

Data Index: 7820328 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.5083. Min Act: -0.1700

Data Index: 1215309 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.4975. Min Act: -0.1700

Data Index: 8097137 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.4998. Min Act: -0.1700

Data Index: 8633101 (Open Web Text)

Max Activating Token Index: 1002

Text #14

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.4999. Min Act: -0.1698

Data Index: 8530771 (Open Web Text)

Max Activating Token Index: 673

Text #15

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.5023. Min Act: -0.1700

Data Index: 7633628 (Open Web Text)

Max Activating Token Index: 428

Text #16

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.4961. Min Act: -0.1700

Data Index: 3049608 (Open Web Text)

Max Activating Token Index: 674

Text #17

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.4904. Min Act: -0.1700

Data Index: 2416999 (Open Web Text)

Max Activating Token Index: 995

Text #18

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.4965. Min Act: -0.1700

Data Index: 8151919 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 1.6149. Min Range: -1.6149

Max Act: 1.4805. Min Act: -0.1700

Data Index: 3841295 (Open Web Text)

Max Activating Token Index: 993