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

Dataset: Open Web Text

Neuron 3006 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: 4.3968. Min Range: -4.3968

Max Act: 4.3968. Min Act: -0.1700

Data Index: 2571873 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.3201. Min Act: -0.1700

Data Index: 3589686 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.3104. Min Act: -0.1700

Data Index: 4507938 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.3154. Min Act: -0.1700

Data Index: 6479764 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.2890. Min Act: -0.1700

Data Index: 5741000 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.2777. Min Act: -0.1700

Data Index: 5307035 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.2675. Min Act: -0.1700

Data Index: 6709899 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.2818. Min Act: -0.1700

Data Index: 1283933 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.2402. Min Act: -0.1700

Data Index: 3863682 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.2451. Min Act: -0.1700

Data Index: 2952923 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.2617. Min Act: -0.1700

Data Index: 5695620 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.2521. Min Act: -0.1700

Data Index: 905590 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.2309. Min Act: -0.1700

Data Index: 8551499 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.2112. Min Act: -0.1700

Data Index: 4306305 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.2190. Min Act: -0.1700

Data Index: 164065 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.2300. Min Act: -0.1700

Data Index: 5678834 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.1947. Min Act: -0.1700

Data Index: 4273739 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.1876. Min Act: -0.1700

Data Index: 5674454 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.1882. Min Act: -0.1700

Data Index: 759953 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.3968. Min Range: -4.3968

Max Act: 4.1879. Min Act: -0.1700

Data Index: 5392131 (Open Web Text)

Max Activating Token Index: 695