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

Dataset: Open Web Text

Neuron 2897 in Layer 0

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: 2.2461. Min Range: -2.2461

Max Act: 2.2461. Min Act: -0.1700

Data Index: 7157070 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.2370. Min Act: -0.1700

Data Index: 8361532 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.2252. Min Act: -0.1700

Data Index: 8271667 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.2220. Min Act: -0.1700

Data Index: 6181957 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.2008. Min Act: -0.1700

Data Index: 4888209 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.2008. Min Act: -0.1700

Data Index: 4146318 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1940. Min Act: -0.1700

Data Index: 4184950 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1849. Min Act: -0.1700

Data Index: 1327944 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1744. Min Act: -0.1700

Data Index: 3864699 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1849. Min Act: -0.1700

Data Index: 2246708 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1849. Min Act: -0.1700

Data Index: 3877323 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1693. Min Act: -0.1700

Data Index: 7033803 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1849. Min Act: -0.1700

Data Index: 7710218 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1576. Min Act: -0.1700

Data Index: 2762376 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1531. Min Act: -0.1700

Data Index: 4669681 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1458. Min Act: -0.1700

Data Index: 7951853 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1482. Min Act: -0.1700

Data Index: 2460620 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1382. Min Act: -0.1700

Data Index: 1961052 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1382. Min Act: -0.1700

Data Index: 2729802 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.2461. Min Range: -2.2461

Max Act: 2.1353. Min Act: -0.1700

Data Index: 5897998 (Open Web Text)

Max Activating Token Index: 10