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

Dataset: Open Web Text

Neuron 2643 in Layer 2

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: 1.1641. Min Range: -1.1641

Max Act: 1.1641. Min Act: -0.1700

Data Index: 1690852 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1641. Min Act: -0.1700

Data Index: 4224882 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1641. Min Act: -0.1700

Data Index: 6293715 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1641. Min Act: -0.1700

Data Index: 771125 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1641. Min Act: -0.1700

Data Index: 6396006 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1641. Min Act: -0.1700

Data Index: 3153544 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1364. Min Act: -0.1700

Data Index: 1215716 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1329. Min Act: -0.1700

Data Index: 2032644 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1262. Min Act: -0.1700

Data Index: 645549 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1234. Min Act: -0.1700

Data Index: 3909165 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1251. Min Act: -0.1700

Data Index: 1204809 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1234. Min Act: -0.1700

Data Index: 6078708 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1234. Min Act: -0.1700

Data Index: 5274207 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1234. Min Act: -0.1700

Data Index: 50801 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1288. Min Act: -0.1700

Data Index: 5189059 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1329. Min Act: -0.1700

Data Index: 2412762 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1234. Min Act: -0.1700

Data Index: 3689417 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1234. Min Act: -0.1700

Data Index: 387069 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1234. Min Act: -0.1700

Data Index: 4389833 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 1.1641. Min Range: -1.1641

Max Act: 1.1262. Min Act: -0.1700

Data Index: 4212173 (Open Web Text)

Max Activating Token Index: 5