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

Dataset: Open Web Text

Neuron 1200 in Layer 4

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: 4.9516. Min Range: -4.9516

Max Act: 4.9516. Min Act: -0.1700

Data Index: 3567827 (Open Web Text)

Max Activating Token Index: 36

Text #1

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.8608. Min Act: -0.1700

Data Index: 1995961 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.7524. Min Act: -0.1700

Data Index: 7416614 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.7177. Min Act: -0.1700

Data Index: 2261549 (Open Web Text)

Max Activating Token Index: 309

Text #4

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.6474. Min Act: -0.1700

Data Index: 8615332 (Open Web Text)

Max Activating Token Index: 63

Text #5

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.6311. Min Act: -0.1700

Data Index: 4115017 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.5942. Min Act: -0.1700

Data Index: 5435845 (Open Web Text)

Max Activating Token Index: 154

Text #7

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.5726. Min Act: -0.1700

Data Index: 7315815 (Open Web Text)

Max Activating Token Index: 67

Text #8

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.5660. Min Act: -0.1700

Data Index: 8081070 (Open Web Text)

Max Activating Token Index: 770

Text #9

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.6088. Min Act: -0.1700

Data Index: 8607351 (Open Web Text)

Max Activating Token Index: 873

Text #10

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.5824. Min Act: -0.1700

Data Index: 7147938 (Open Web Text)

Max Activating Token Index: 927

Text #11

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.5185. Min Act: -0.1700

Data Index: 6693941 (Open Web Text)

Max Activating Token Index: 916

Text #12

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.5221. Min Act: -0.1700

Data Index: 4352043 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.5479. Min Act: -0.1700

Data Index: 8561818 (Open Web Text)

Max Activating Token Index: 653

Text #14

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.5319. Min Act: -0.1700

Data Index: 3974123 (Open Web Text)

Max Activating Token Index: 603

Text #15

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.5408. Min Act: -0.1700

Data Index: 4846228 (Open Web Text)

Max Activating Token Index: 688

Text #16

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.4872. Min Act: -0.1700

Data Index: 7507950 (Open Web Text)

Max Activating Token Index: 139

Text #17

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.4701. Min Act: -0.1700

Data Index: 6830200 (Open Web Text)

Max Activating Token Index: 199

Text #18

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.4451. Min Act: -0.1700

Data Index: 4217679 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 4.9516. Min Range: -4.9516

Max Act: 4.4052. Min Act: -0.1700

Data Index: 6702432 (Open Web Text)

Max Activating Token Index: 137