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

Dataset: Open Web Text

Neuron 489 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: 2.7618. Min Range: -2.7618

Max Act: 2.7618. Min Act: -0.1700

Data Index: 7782668 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.7291. Min Act: -0.1700

Data Index: 7782666 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.7168. Min Act: -0.1700

Data Index: 1427596 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6899. Min Act: -0.1700

Data Index: 2389484 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6901. Min Act: -0.1700

Data Index: 7219237 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6932. Min Act: -0.1700

Data Index: 3073561 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.7005. Min Act: -0.1700

Data Index: 8663692 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6997. Min Act: -0.1700

Data Index: 5309990 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6818. Min Act: -0.1700

Data Index: 8118918 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6916. Min Act: -0.1700

Data Index: 5128114 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6792. Min Act: -0.1700

Data Index: 1085280 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6736. Min Act: -0.1700

Data Index: 7527031 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6749. Min Act: -0.1700

Data Index: 6083711 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6697. Min Act: -0.1700

Data Index: 5352653 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6629. Min Act: -0.1700

Data Index: 8160791 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6536. Min Act: -0.1700

Data Index: 4567870 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6548. Min Act: -0.1700

Data Index: 1465330 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6461. Min Act: -0.1700

Data Index: 6034879 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6470. Min Act: -0.1700

Data Index: 6482525 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.6441. Min Act: -0.1700

Data Index: 7291894 (Open Web Text)

Max Activating Token Index: 3