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

Dataset: Open Web Text

Neuron 2946 in Layer 4

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: 3.5791. Min Range: -3.5791

Max Act: 3.5307. Min Act: -0.1700

Data Index: 4095025 (Open Web Text)

Max Activating Token Index: 648

Text #1

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.5791. Min Act: -0.1700

Data Index: 4366343 (Open Web Text)

Max Activating Token Index: 541

Text #2

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4934. Min Act: -0.1700

Data Index: 5127666 (Open Web Text)

Max Activating Token Index: 986

Text #3

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4792. Min Act: -0.1700

Data Index: 8204879 (Open Web Text)

Max Activating Token Index: 296

Text #4

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4877. Min Act: -0.1700

Data Index: 733516 (Open Web Text)

Max Activating Token Index: 162

Text #5

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4731. Min Act: -0.1700

Data Index: 2852658 (Open Web Text)

Max Activating Token Index: 67

Text #6

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4641. Min Act: -0.1700

Data Index: 4500461 (Open Web Text)

Max Activating Token Index: 413

Text #7

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4754. Min Act: -0.1700

Data Index: 4299465 (Open Web Text)

Max Activating Token Index: 123

Text #8

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4589. Min Act: -0.1700

Data Index: 7441522 (Open Web Text)

Max Activating Token Index: 166

Text #9

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4501. Min Act: -0.1700

Data Index: 6269098 (Open Web Text)

Max Activating Token Index: 79

Text #10

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4599. Min Act: -0.1700

Data Index: 7098724 (Open Web Text)

Max Activating Token Index: 801

Text #11

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4380. Min Act: -0.1700

Data Index: 8476853 (Open Web Text)

Max Activating Token Index: 514

Text #12

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4793. Min Act: -0.1700

Data Index: 7364450 (Open Web Text)

Max Activating Token Index: 564

Text #13

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4231. Min Act: -0.1700

Data Index: 6815990 (Open Web Text)

Max Activating Token Index: 355

Text #14

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4408. Min Act: -0.1700

Data Index: 5272759 (Open Web Text)

Max Activating Token Index: 841

Text #15

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4301. Min Act: -0.1700

Data Index: 3919788 (Open Web Text)

Max Activating Token Index: 745

Text #16

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4058. Min Act: -0.1700

Data Index: 982666 (Open Web Text)

Max Activating Token Index: 98

Text #17

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.4217. Min Act: -0.1700

Data Index: 859784 (Open Web Text)

Max Activating Token Index: 877

Text #18

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.3592. Min Act: -0.1700

Data Index: 608071 (Open Web Text)

Max Activating Token Index: 436

Text #19

Max Range: 3.5791. Min Range: -3.5791

Max Act: 3.3872. Min Act: -0.1700

Data Index: 3840497 (Open Web Text)

Max Activating Token Index: 129