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

Dataset: Open Web Text

Neuron 2459 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: 4.3182. Min Range: -4.3182

Max Act: 4.3182. Min Act: -0.1700

Data Index: 7667880 (Open Web Text)

Max Activating Token Index: 217

Text #1

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.2902. Min Act: -0.1700

Data Index: 3652852 (Open Web Text)

Max Activating Token Index: 388

Text #2

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.2761. Min Act: -0.1700

Data Index: 4450353 (Open Web Text)

Max Activating Token Index: 939

Text #3

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.2813. Min Act: -0.1700

Data Index: 2599164 (Open Web Text)

Max Activating Token Index: 971

Text #4

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.2560. Min Act: -0.1700

Data Index: 5647581 (Open Web Text)

Max Activating Token Index: 857

Text #5

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.2489. Min Act: -0.1700

Data Index: 3119881 (Open Web Text)

Max Activating Token Index: 984

Text #6

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.2154. Min Act: -0.1700

Data Index: 3436137 (Open Web Text)

Max Activating Token Index: 575

Text #7

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.2092. Min Act: -0.1700

Data Index: 7656101 (Open Web Text)

Max Activating Token Index: 437

Text #8

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.1652. Min Act: -0.1700

Data Index: 6317911 (Open Web Text)

Max Activating Token Index: 845

Text #9

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.1828. Min Act: -0.1700

Data Index: 277980 (Open Web Text)

Max Activating Token Index: 434

Text #10

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.1166. Min Act: -0.1700

Data Index: 971597 (Open Web Text)

Max Activating Token Index: 461

Text #11

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.1366. Min Act: -0.1700

Data Index: 7839477 (Open Web Text)

Max Activating Token Index: 516

Text #12

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.1203. Min Act: -0.1700

Data Index: 6152572 (Open Web Text)

Max Activating Token Index: 582

Text #13

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.0982. Min Act: -0.1700

Data Index: 3969438 (Open Web Text)

Max Activating Token Index: 992

Text #14

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.1524. Min Act: -0.1700

Data Index: 8763992 (Open Web Text)

Max Activating Token Index: 901

Text #15

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.1121. Min Act: -0.1700

Data Index: 5598658 (Open Web Text)

Max Activating Token Index: 293

Text #16

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.1109. Min Act: -0.1700

Data Index: 5175168 (Open Web Text)

Max Activating Token Index: 748

Text #17

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.1298. Min Act: -0.1700

Data Index: 7177520 (Open Web Text)

Max Activating Token Index: 732

Text #18

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.1205. Min Act: -0.1700

Data Index: 6281162 (Open Web Text)

Max Activating Token Index: 59

Text #19

Max Range: 4.3182. Min Range: -4.3182

Max Act: 4.0825. Min Act: -0.1700

Data Index: 1563625 (Open Web Text)

Max Activating Token Index: 116