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

Dataset: Open Web Text

Neuron 374 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: 5.4473. Min Range: -5.4473

Max Act: 5.4473. Min Act: -0.1700

Data Index: 5743689 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.4464. Min Act: -0.1700

Data Index: 8494039 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.4221. Min Act: -0.1700

Data Index: 1789036 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.4184. Min Act: -0.1700

Data Index: 838079 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.4236. Min Act: -0.1700

Data Index: 28003 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.4281. Min Act: -0.1700

Data Index: 1665396 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.3847. Min Act: -0.1700

Data Index: 6694971 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.4107. Min Act: -0.1700

Data Index: 7505588 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.4018. Min Act: -0.1700

Data Index: 508044 (Open Web Text)

Max Activating Token Index: 982

Text #9

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.4156. Min Act: -0.1700

Data Index: 1095702 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.4164. Min Act: -0.1700

Data Index: 1772412 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.3640. Min Act: -0.1700

Data Index: 1159102 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.3420. Min Act: -0.1700

Data Index: 5350932 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.3746. Min Act: -0.1700

Data Index: 3801301 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.3427. Min Act: -0.1700

Data Index: 1109883 (Open Web Text)

Max Activating Token Index: 698

Text #15

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.3347. Min Act: -0.1700

Data Index: 5270110 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.3415. Min Act: -0.1700

Data Index: 1026085 (Open Web Text)

Max Activating Token Index: 712

Text #17

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.3509. Min Act: -0.1700

Data Index: 1592781 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.3378. Min Act: -0.1700

Data Index: 96631 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 5.4473. Min Range: -5.4473

Max Act: 5.3144. Min Act: -0.1700

Data Index: 4277729 (Open Web Text)

Max Activating Token Index: 520