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

Dataset: Open Web Text

Neuron 1187 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: 2.8999. Min Range: -2.8999

Max Act: 2.8999. Min Act: -0.1700

Data Index: 5666054 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8760. Min Act: -0.1700

Data Index: 6509319 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8646. Min Act: -0.1700

Data Index: 3972006 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8597. Min Act: -0.1700

Data Index: 2732193 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8646. Min Act: -0.1700

Data Index: 2336410 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8626. Min Act: -0.1700

Data Index: 604650 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8547. Min Act: -0.1700

Data Index: 6092763 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8564. Min Act: -0.1700

Data Index: 2426775 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8377. Min Act: -0.1700

Data Index: 5371177 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8083. Min Act: -0.1700

Data Index: 8583868 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8079. Min Act: -0.1700

Data Index: 486306 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8147. Min Act: -0.1700

Data Index: 5981942 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8003. Min Act: -0.1700

Data Index: 2027207 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8087. Min Act: -0.1700

Data Index: 2949042 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8087. Min Act: -0.1700

Data Index: 1721692 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8086. Min Act: -0.1700

Data Index: 2511115 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.7898. Min Act: -0.1700

Data Index: 886714 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8087. Min Act: -0.1700

Data Index: 5728972 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8087. Min Act: -0.1700

Data Index: 3752670 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.8999. Min Range: -2.8999

Max Act: 2.8087. Min Act: -0.1700

Data Index: 1879002 (Open Web Text)

Max Activating Token Index: 2