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

Dataset: Open Web Text

Neuron 382 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: 4.8694. Min Range: -4.8694

Max Act: 4.8694. Min Act: -0.1700

Data Index: 5375708 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.7235. Min Act: -0.1700

Data Index: 4676751 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.6727. Min Act: -0.1700

Data Index: 312837 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.6535. Min Act: -0.1700

Data Index: 3566710 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.6423. Min Act: -0.1700

Data Index: 8611301 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.6086. Min Act: -0.1700

Data Index: 4785857 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5899. Min Act: -0.1700

Data Index: 1153270 (Open Web Text)

Max Activating Token Index: 63

Text #7

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5961. Min Act: -0.1700

Data Index: 1603649 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5828. Min Act: -0.1700

Data Index: 688142 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5677. Min Act: -0.1700

Data Index: 5239175 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5668. Min Act: -0.1700

Data Index: 2739984 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5718. Min Act: -0.1700

Data Index: 6141862 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5628. Min Act: -0.1700

Data Index: 1896450 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5676. Min Act: -0.1700

Data Index: 6141859 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5657. Min Act: -0.1700

Data Index: 4390981 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5347. Min Act: -0.1700

Data Index: 5103042 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5385. Min Act: -0.1700

Data Index: 1779006 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5393. Min Act: -0.1700

Data Index: 6142894 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5533. Min Act: -0.1700

Data Index: 1923998 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.8694. Min Range: -4.8694

Max Act: 4.5151. Min Act: -0.1700

Data Index: 4465104 (Open Web Text)

Max Activating Token Index: 9