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

Dataset: Open Web Text

Neuron 2570 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: 1.9896. Min Range: -1.9896

Max Act: 1.9896. Min Act: -0.1700

Data Index: 3173307 (Open Web Text)

Max Activating Token Index: 829

Text #1

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9891. Min Act: -0.1700

Data Index: 1360739 (Open Web Text)

Max Activating Token Index: 530

Text #2

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9491. Min Act: -0.1700

Data Index: 8560464 (Open Web Text)

Max Activating Token Index: 297

Text #3

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9407. Min Act: -0.1700

Data Index: 8158248 (Open Web Text)

Max Activating Token Index: 682

Text #4

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9449. Min Act: -0.1700

Data Index: 4082274 (Open Web Text)

Max Activating Token Index: 960

Text #5

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9326. Min Act: -0.1700

Data Index: 4930908 (Open Web Text)

Max Activating Token Index: 776

Text #6

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9149. Min Act: -0.1700

Data Index: 7019636 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9178. Min Act: -0.1700

Data Index: 7940842 (Open Web Text)

Max Activating Token Index: 212

Text #8

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9310. Min Act: -0.1700

Data Index: 8551073 (Open Web Text)

Max Activating Token Index: 895

Text #9

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9239. Min Act: -0.1700

Data Index: 7945705 (Open Web Text)

Max Activating Token Index: 363

Text #10

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.8954. Min Act: -0.1700

Data Index: 7111474 (Open Web Text)

Max Activating Token Index: 324

Text #11

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.8906. Min Act: -0.1700

Data Index: 1422712 (Open Web Text)

Max Activating Token Index: 170

Text #12

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9075. Min Act: -0.1700

Data Index: 4974368 (Open Web Text)

Max Activating Token Index: 628

Text #13

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9084. Min Act: -0.1699

Data Index: 4555060 (Open Web Text)

Max Activating Token Index: 992

Text #14

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.8801. Min Act: -0.1700

Data Index: 7625510 (Open Web Text)

Max Activating Token Index: 651

Text #15

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.8990. Min Act: -0.1700

Data Index: 7841192 (Open Web Text)

Max Activating Token Index: 833

Text #16

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9026. Min Act: -0.1700

Data Index: 6550024 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.8829. Min Act: -0.1700

Data Index: 7611245 (Open Web Text)

Max Activating Token Index: 763

Text #18

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.8954. Min Act: -0.1700

Data Index: 3394641 (Open Web Text)

Max Activating Token Index: 889

Text #19

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.8679. Min Act: -0.1700

Data Index: 7784215 (Open Web Text)

Max Activating Token Index: 209