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

Dataset: Open Web Text

Neuron 532 in Layer 3

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: 2.5787. Min Range: -2.5787

Max Act: 2.5656. Min Act: -0.1700

Data Index: 6438448 (Open Web Text)

Max Activating Token Index: 823

Text #1

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.5787. Min Act: -0.1700

Data Index: 7898389 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.5465. Min Act: -0.1700

Data Index: 4543968 (Open Web Text)

Max Activating Token Index: 903

Text #3

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.5466. Min Act: -0.1700

Data Index: 1864574 (Open Web Text)

Max Activating Token Index: 274

Text #4

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.5175. Min Act: -0.1700

Data Index: 1145340 (Open Web Text)

Max Activating Token Index: 38

Text #5

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.4704. Min Act: -0.1700

Data Index: 400244 (Open Web Text)

Max Activating Token Index: 794

Text #6

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.5057. Min Act: -0.1700

Data Index: 4520542 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.4941. Min Act: -0.1700

Data Index: 2678072 (Open Web Text)

Max Activating Token Index: 171

Text #8

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.5151. Min Act: -0.1700

Data Index: 8566972 (Open Web Text)

Max Activating Token Index: 1010

Text #9

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.4615. Min Act: -0.1700

Data Index: 5602929 (Open Web Text)

Max Activating Token Index: 407

Text #10

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.4849. Min Act: -0.1700

Data Index: 1735327 (Open Web Text)

Max Activating Token Index: 417

Text #11

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.4419. Min Act: -0.1700

Data Index: 1687660 (Open Web Text)

Max Activating Token Index: 777

Text #12

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.5276. Min Act: -0.1700

Data Index: 6611814 (Open Web Text)

Max Activating Token Index: 866

Text #13

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.5064. Min Act: -0.1700

Data Index: 2159632 (Open Web Text)

Max Activating Token Index: 281

Text #14

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.4807. Min Act: -0.1700

Data Index: 683808 (Open Web Text)

Max Activating Token Index: 406

Text #15

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.4737. Min Act: -0.1700

Data Index: 3100757 (Open Web Text)

Max Activating Token Index: 852

Text #16

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.4465. Min Act: -0.1700

Data Index: 4634619 (Open Web Text)

Max Activating Token Index: 107

Text #17

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.4677. Min Act: -0.1700

Data Index: 6327775 (Open Web Text)

Max Activating Token Index: 656

Text #18

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.4620. Min Act: -0.1700

Data Index: 6131454 (Open Web Text)

Max Activating Token Index: 777

Text #19

Max Range: 2.5787. Min Range: -2.5787

Max Act: 2.4655. Min Act: -0.1700

Data Index: 7317914 (Open Web Text)

Max Activating Token Index: 524