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

Dataset: Open Web Text

Neuron 7 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: 2.8980. Min Range: -2.8980

Max Act: 2.8980. Min Act: -0.1700

Data Index: 8005127 (Open Web Text)

Max Activating Token Index: 998

Text #1

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.8268. Min Act: -0.1700

Data Index: 250982 (Open Web Text)

Max Activating Token Index: 976

Text #2

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.8192. Min Act: -0.1700

Data Index: 4514350 (Open Web Text)

Max Activating Token Index: 963

Text #3

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.7544. Min Act: -0.1700

Data Index: 3767595 (Open Web Text)

Max Activating Token Index: 595

Text #4

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.7459. Min Act: -0.1700

Data Index: 583709 (Open Web Text)

Max Activating Token Index: 1010

Text #5

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.7096. Min Act: -0.1700

Data Index: 8247287 (Open Web Text)

Max Activating Token Index: 593

Text #6

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.6698. Min Act: -0.1700

Data Index: 3197993 (Open Web Text)

Max Activating Token Index: 1007

Text #7

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.7172. Min Act: -0.1700

Data Index: 1581014 (Open Web Text)

Max Activating Token Index: 975

Text #8

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.6979. Min Act: -0.1700

Data Index: 1468028 (Open Web Text)

Max Activating Token Index: 1008

Text #9

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.6563. Min Act: -0.1700

Data Index: 583711 (Open Web Text)

Max Activating Token Index: 1004

Text #10

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.6720. Min Act: -0.1700

Data Index: 2921841 (Open Web Text)

Max Activating Token Index: 981

Text #11

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.6467. Min Act: -0.1700

Data Index: 3767593 (Open Web Text)

Max Activating Token Index: 741

Text #12

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.6405. Min Act: -0.1700

Data Index: 6887761 (Open Web Text)

Max Activating Token Index: 989

Text #13

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.6729. Min Act: -0.1700

Data Index: 8748854 (Open Web Text)

Max Activating Token Index: 979

Text #14

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.6240. Min Act: -0.1700

Data Index: 3120042 (Open Web Text)

Max Activating Token Index: 811

Text #15

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.6341. Min Act: -0.1700

Data Index: 1248652 (Open Web Text)

Max Activating Token Index: 866

Text #16

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.5917. Min Act: -0.1700

Data Index: 4993225 (Open Web Text)

Max Activating Token Index: 981

Text #17

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.5859. Min Act: -0.1700

Data Index: 6092131 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.5910. Min Act: -0.1700

Data Index: 3340466 (Open Web Text)

Max Activating Token Index: 981

Text #19

Max Range: 2.8980. Min Range: -2.8980

Max Act: 2.5901. Min Act: -0.1700

Data Index: 4665872 (Open Web Text)

Max Activating Token Index: 898