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

Dataset: Open Web Text

Neuron 1030 in Layer 3

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: 3.7739. Min Range: -3.7739

Max Act: 3.7739. Min Act: -0.1700

Data Index: 6687447 (Open Web Text)

Max Activating Token Index: 173

Text #1

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.6996. Min Act: -0.1700

Data Index: 3809089 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.6333. Min Act: -0.1700

Data Index: 4237712 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.6281. Min Act: -0.1700

Data Index: 2855214 (Open Web Text)

Max Activating Token Index: 491

Text #4

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.6077. Min Act: -0.1700

Data Index: 860621 (Open Web Text)

Max Activating Token Index: 818

Text #5

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.6414. Min Act: -0.1700

Data Index: 8559325 (Open Web Text)

Max Activating Token Index: 206

Text #6

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5765. Min Act: -0.1700

Data Index: 378541 (Open Web Text)

Max Activating Token Index: 459

Text #7

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5819. Min Act: -0.1700

Data Index: 5536479 (Open Web Text)

Max Activating Token Index: 691

Text #8

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5574. Min Act: -0.1700

Data Index: 1777158 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5889. Min Act: -0.1700

Data Index: 55960 (Open Web Text)

Max Activating Token Index: 393

Text #10

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5345. Min Act: -0.1700

Data Index: 8250900 (Open Web Text)

Max Activating Token Index: 253

Text #11

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5744. Min Act: -0.1700

Data Index: 8132131 (Open Web Text)

Max Activating Token Index: 170

Text #12

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5288. Min Act: -0.1700

Data Index: 521508 (Open Web Text)

Max Activating Token Index: 691

Text #13

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5171. Min Act: -0.1700

Data Index: 6006354 (Open Web Text)

Max Activating Token Index: 259

Text #14

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5425. Min Act: -0.1700

Data Index: 3022815 (Open Web Text)

Max Activating Token Index: 63

Text #15

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5199. Min Act: -0.1700

Data Index: 47786 (Open Web Text)

Max Activating Token Index: 939

Text #16

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5345. Min Act: -0.1700

Data Index: 6132929 (Open Web Text)

Max Activating Token Index: 237

Text #17

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5202. Min Act: -0.1700

Data Index: 5209470 (Open Web Text)

Max Activating Token Index: 655

Text #18

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5153. Min Act: -0.1700

Data Index: 3686200 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.7739. Min Range: -3.7739

Max Act: 3.5060. Min Act: -0.1700

Data Index: 6709586 (Open Web Text)

Max Activating Token Index: 828