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

Dataset: Open Web Text

Neuron 2774 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: 5.3036. Min Range: -5.3036

Max Act: 5.3036. Min Act: -0.1700

Data Index: 6625577 (Open Web Text)

Max Activating Token Index: 957

Text #1

Max Range: 5.3036. Min Range: -5.3036

Max Act: 5.1573. Min Act: -0.1700

Data Index: 4264237 (Open Web Text)

Max Activating Token Index: 458

Text #2

Max Range: 5.3036. Min Range: -5.3036

Max Act: 5.1206. Min Act: -0.1700

Data Index: 3181398 (Open Web Text)

Max Activating Token Index: 187

Text #3

Max Range: 5.3036. Min Range: -5.3036

Max Act: 5.1050. Min Act: -0.1700

Data Index: 1649910 (Open Web Text)

Max Activating Token Index: 644

Text #4

Max Range: 5.3036. Min Range: -5.3036

Max Act: 5.1189. Min Act: -0.1700

Data Index: 6876835 (Open Web Text)

Max Activating Token Index: 762

Text #5

Max Range: 5.3036. Min Range: -5.3036

Max Act: 5.0566. Min Act: -0.1700

Data Index: 6081798 (Open Web Text)

Max Activating Token Index: 217

Text #6

Max Range: 5.3036. Min Range: -5.3036

Max Act: 5.0420. Min Act: -0.1700

Data Index: 5379530 (Open Web Text)

Max Activating Token Index: 78

Text #7

Max Range: 5.3036. Min Range: -5.3036

Max Act: 5.0082. Min Act: -0.1699

Data Index: 935057 (Open Web Text)

Max Activating Token Index: 742

Text #8

Max Range: 5.3036. Min Range: -5.3036

Max Act: 5.0240. Min Act: -0.1700

Data Index: 7188188 (Open Web Text)

Max Activating Token Index: 190

Text #9

Max Range: 5.3036. Min Range: -5.3036

Max Act: 5.0655. Min Act: -0.1700

Data Index: 2549007 (Open Web Text)

Max Activating Token Index: 870

Text #10

Max Range: 5.3036. Min Range: -5.3036

Max Act: 4.9789. Min Act: -0.1700

Data Index: 8741436 (Open Web Text)

Max Activating Token Index: 403

Text #11

Max Range: 5.3036. Min Range: -5.3036

Max Act: 5.0006. Min Act: -0.1700

Data Index: 8145778 (Open Web Text)

Max Activating Token Index: 705

Text #12

Max Range: 5.3036. Min Range: -5.3036

Max Act: 4.9990. Min Act: -0.1700

Data Index: 6218715 (Open Web Text)

Max Activating Token Index: 399

Text #13

Max Range: 5.3036. Min Range: -5.3036

Max Act: 4.9521. Min Act: -0.1700

Data Index: 5954002 (Open Web Text)

Max Activating Token Index: 863

Text #14

Max Range: 5.3036. Min Range: -5.3036

Max Act: 4.9552. Min Act: -0.1700

Data Index: 5152397 (Open Web Text)

Max Activating Token Index: 340

Text #15

Max Range: 5.3036. Min Range: -5.3036

Max Act: 4.9502. Min Act: -0.1700

Data Index: 7395522 (Open Web Text)

Max Activating Token Index: 408

Text #16

Max Range: 5.3036. Min Range: -5.3036

Max Act: 4.9915. Min Act: -0.1700

Data Index: 6064251 (Open Web Text)

Max Activating Token Index: 492

Text #17

Max Range: 5.3036. Min Range: -5.3036

Max Act: 4.9983. Min Act: -0.1700

Data Index: 4098194 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 5.3036. Min Range: -5.3036

Max Act: 4.9223. Min Act: -0.1700

Data Index: 5012342 (Open Web Text)

Max Activating Token Index: 823

Text #19

Max Range: 5.3036. Min Range: -5.3036

Max Act: 4.9015. Min Act: -0.1700

Data Index: 5978280 (Open Web Text)

Max Activating Token Index: 891