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

Dataset: Open Web Text

Neuron 2208 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: 2.5790. Min Range: -2.5790

Max Act: 2.5790. Min Act: -0.1700

Data Index: 134617 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5647. Min Act: -0.1700

Data Index: 5329328 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5647. Min Act: -0.1700

Data Index: 1473236 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5647. Min Act: -0.1700

Data Index: 6112804 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5647. Min Act: -0.1700

Data Index: 940805 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5647. Min Act: -0.1700

Data Index: 7546615 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5647. Min Act: -0.1700

Data Index: 6306961 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5647. Min Act: -0.1700

Data Index: 4065541 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5539. Min Act: -0.1700

Data Index: 2107507 (Open Web Text)

Max Activating Token Index: 77

Text #9

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5356. Min Act: -0.1700

Data Index: 4045781 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5338. Min Act: -0.1700

Data Index: 1944727 (Open Web Text)

Max Activating Token Index: 495

Text #11

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5283. Min Act: -0.1700

Data Index: 8322044 (Open Web Text)

Max Activating Token Index: 421

Text #12

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5374. Min Act: -0.1700

Data Index: 3861209 (Open Web Text)

Max Activating Token Index: 35

Text #13

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5193. Min Act: -0.1700

Data Index: 1151897 (Open Web Text)

Max Activating Token Index: 1017

Text #14

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5138. Min Act: -0.1700

Data Index: 1938544 (Open Web Text)

Max Activating Token Index: 139

Text #15

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5156. Min Act: -0.1700

Data Index: 7465243 (Open Web Text)

Max Activating Token Index: 46

Text #16

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5052. Min Act: -0.1700

Data Index: 3264694 (Open Web Text)

Max Activating Token Index: 543

Text #17

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5277. Min Act: -0.1700

Data Index: 6435858 (Open Web Text)

Max Activating Token Index: 407

Text #18

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.5078. Min Act: -0.1700

Data Index: 6474248 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.5790. Min Range: -2.5790

Max Act: 2.4769. Min Act: -0.1700

Data Index: 2195308 (Open Web Text)

Max Activating Token Index: 375