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

Dataset: Open Web Text

Neuron 981 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: 3.3885. Min Range: -3.3885

Max Act: 3.3885. Min Act: -0.1700

Data Index: 578008 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.2502. Min Act: -0.1700

Data Index: 950673 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.2558. Min Act: -0.1700

Data Index: 3255674 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.2492. Min Act: -0.1700

Data Index: 7692236 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.2101. Min Act: -0.1700

Data Index: 1369156 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.2043. Min Act: -0.1700

Data Index: 5895730 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.1933. Min Act: -0.1700

Data Index: 1275076 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.1465. Min Act: -0.1700

Data Index: 2073426 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.1420. Min Act: -0.1700

Data Index: 7774357 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.1301. Min Act: -0.1700

Data Index: 4935972 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.1132. Min Act: -0.1700

Data Index: 5493773 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.1312. Min Act: -0.1700

Data Index: 110830 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.1251. Min Act: -0.1700

Data Index: 7003841 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.1101. Min Act: -0.1700

Data Index: 8468445 (Open Web Text)

Max Activating Token Index: 20

Text #14

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.0933. Min Act: -0.1700

Data Index: 3032428 (Open Web Text)

Max Activating Token Index: 60

Text #15

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.0756. Min Act: -0.1700

Data Index: 6491632 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.0734. Min Act: -0.1700

Data Index: 6147265 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.0849. Min Act: -0.1700

Data Index: 437786 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.0734. Min Act: -0.1700

Data Index: 7217701 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.3885. Min Range: -3.3885

Max Act: 3.0819. Min Act: -0.1700

Data Index: 73657 (Open Web Text)

Max Activating Token Index: 71