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

Dataset: Open Web Text

Neuron 1475 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: 4.5331. Min Range: -4.5331

Max Act: 4.5331. Min Act: -0.1700

Data Index: 5643149 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.5052. Min Act: -0.1700

Data Index: 10787 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.4903. Min Act: -0.1700

Data Index: 845106 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.4903. Min Act: -0.1700

Data Index: 2652102 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.4255. Min Act: -0.1700

Data Index: 5067247 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.4276. Min Act: -0.1700

Data Index: 2114415 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.4409. Min Act: -0.1700

Data Index: 1202973 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.3943. Min Act: -0.1700

Data Index: 6782768 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.4066. Min Act: -0.1700

Data Index: 6894680 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.3759. Min Act: -0.1700

Data Index: 2595893 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.3624. Min Act: -0.1700

Data Index: 2727276 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.3760. Min Act: -0.1700

Data Index: 5884712 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.3408. Min Act: -0.1700

Data Index: 4078332 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.3393. Min Act: -0.1700

Data Index: 4664909 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.3492. Min Act: -0.1700

Data Index: 1583078 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.3377. Min Act: -0.1700

Data Index: 6418297 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.3354. Min Act: -0.1700

Data Index: 268068 (Open Web Text)

Max Activating Token Index: 42

Text #17

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.3512. Min Act: -0.1700

Data Index: 3921319 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.3463. Min Act: -0.1700

Data Index: 1778542 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.5331. Min Range: -4.5331

Max Act: 4.3399. Min Act: -0.1700

Data Index: 2276047 (Open Web Text)

Max Activating Token Index: 3