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

Dataset: Open Web Text

Neuron 1224 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: 3.3561. Min Range: -3.3561

Max Act: 3.3561. Min Act: -0.1700

Data Index: 1997168 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2965. Min Act: -0.1700

Data Index: 318003 (Open Web Text)

Max Activating Token Index: 687

Text #2

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2865. Min Act: -0.1700

Data Index: 1256372 (Open Web Text)

Max Activating Token Index: 950

Text #3

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2427. Min Act: -0.1700

Data Index: 1198875 (Open Web Text)

Max Activating Token Index: 850

Text #4

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2273. Min Act: -0.1700

Data Index: 766805 (Open Web Text)

Max Activating Token Index: 136

Text #5

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2263. Min Act: -0.1700

Data Index: 7230549 (Open Web Text)

Max Activating Token Index: 142

Text #6

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2105. Min Act: -0.1700

Data Index: 210764 (Open Web Text)

Max Activating Token Index: 356

Text #7

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2178. Min Act: -0.1700

Data Index: 215768 (Open Web Text)

Max Activating Token Index: 825

Text #8

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2130. Min Act: -0.1700

Data Index: 4017669 (Open Web Text)

Max Activating Token Index: 136

Text #9

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2134. Min Act: -0.1700

Data Index: 1617197 (Open Web Text)

Max Activating Token Index: 23

Text #10

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1978. Min Act: -0.1700

Data Index: 7545056 (Open Web Text)

Max Activating Token Index: 645

Text #11

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1983. Min Act: -0.1700

Data Index: 1014150 (Open Web Text)

Max Activating Token Index: 151

Text #12

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2023. Min Act: -0.1700

Data Index: 4528669 (Open Web Text)

Max Activating Token Index: 770

Text #13

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1964. Min Act: -0.1700

Data Index: 5077023 (Open Web Text)

Max Activating Token Index: 37

Text #14

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2089. Min Act: -0.1700

Data Index: 1574104 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.2074. Min Act: -0.1700

Data Index: 5573588 (Open Web Text)

Max Activating Token Index: 481

Text #16

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1942. Min Act: -0.1700

Data Index: 6470842 (Open Web Text)

Max Activating Token Index: 881

Text #17

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1952. Min Act: -0.1700

Data Index: 6853284 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1949. Min Act: -0.1700

Data Index: 230457 (Open Web Text)

Max Activating Token Index: 759

Text #19

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.1886. Min Act: -0.1700

Data Index: 3292570 (Open Web Text)

Max Activating Token Index: 521