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

Dataset: Open Web Text

Neuron 2810 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: 1.6802. Min Range: -1.6802

Max Act: 1.6802. Min Act: -0.1700

Data Index: 6236147 (Open Web Text)

Max Activating Token Index: 198

Text #1

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6327. Min Act: -0.1695

Data Index: 5472406 (Open Web Text)

Max Activating Token Index: 912

Text #2

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6450. Min Act: -0.1700

Data Index: 6294592 (Open Web Text)

Max Activating Token Index: 165

Text #3

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6415. Min Act: -0.1700

Data Index: 8631864 (Open Web Text)

Max Activating Token Index: 242

Text #4

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6435. Min Act: -0.1700

Data Index: 5251162 (Open Web Text)

Max Activating Token Index: 668

Text #5

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6396. Min Act: -0.1700

Data Index: 60811 (Open Web Text)

Max Activating Token Index: 211

Text #6

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6400. Min Act: -0.1700

Data Index: 3565588 (Open Web Text)

Max Activating Token Index: 592

Text #7

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6413. Min Act: -0.1700

Data Index: 3564119 (Open Web Text)

Max Activating Token Index: 669

Text #8

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6286. Min Act: -0.1698

Data Index: 4880364 (Open Web Text)

Max Activating Token Index: 146

Text #9

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6267. Min Act: -0.1699

Data Index: 2681090 (Open Web Text)

Max Activating Token Index: 908

Text #10

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6308. Min Act: -0.1700

Data Index: 7784943 (Open Web Text)

Max Activating Token Index: 58

Text #11

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6188. Min Act: -0.1700

Data Index: 6370522 (Open Web Text)

Max Activating Token Index: 642

Text #12

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6272. Min Act: -0.1700

Data Index: 7157786 (Open Web Text)

Max Activating Token Index: 890

Text #13

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6003. Min Act: -0.1700

Data Index: 4981797 (Open Web Text)

Max Activating Token Index: 704

Text #14

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6013. Min Act: -0.1700

Data Index: 5251164 (Open Web Text)

Max Activating Token Index: 183

Text #15

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.5994. Min Act: -0.1700

Data Index: 1326603 (Open Web Text)

Max Activating Token Index: 153

Text #16

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.5878. Min Act: -0.1700

Data Index: 1425201 (Open Web Text)

Max Activating Token Index: 501

Text #17

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.5788. Min Act: -0.1700

Data Index: 994496 (Open Web Text)

Max Activating Token Index: 484

Text #18

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.5873. Min Act: -0.1700

Data Index: 7448884 (Open Web Text)

Max Activating Token Index: 686

Text #19

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.5757. Min Act: -0.1700

Data Index: 5228865 (Open Web Text)

Max Activating Token Index: 463