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

Dataset: Open Web Text

Neuron 438 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: 3.2787. Min Range: -3.2787

Max Act: 3.2787. Min Act: -0.1700

Data Index: 1833584 (Open Web Text)

Max Activating Token Index: 805

Text #1

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.2751. Min Act: -0.1700

Data Index: 3232547 (Open Web Text)

Max Activating Token Index: 361

Text #2

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.2747. Min Act: -0.1700

Data Index: 3103867 (Open Web Text)

Max Activating Token Index: 353

Text #3

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1650. Min Act: -0.1700

Data Index: 908274 (Open Web Text)

Max Activating Token Index: 406

Text #4

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1534. Min Act: -0.1700

Data Index: 1217193 (Open Web Text)

Max Activating Token Index: 445

Text #5

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1658. Min Act: -0.1700

Data Index: 3889006 (Open Web Text)

Max Activating Token Index: 841

Text #6

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1235. Min Act: -0.1700

Data Index: 5275176 (Open Web Text)

Max Activating Token Index: 118

Text #7

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1171. Min Act: -0.1700

Data Index: 2012077 (Open Web Text)

Max Activating Token Index: 340

Text #8

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0766. Min Act: -0.1700

Data Index: 85819 (Open Web Text)

Max Activating Token Index: 716

Text #9

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0427. Min Act: -0.1700

Data Index: 5598727 (Open Web Text)

Max Activating Token Index: 1019

Text #10

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0671. Min Act: -0.1700

Data Index: 3569834 (Open Web Text)

Max Activating Token Index: 87

Text #11

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0676. Min Act: -0.1700

Data Index: 5298104 (Open Web Text)

Max Activating Token Index: 830

Text #12

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0588. Min Act: -0.1700

Data Index: 6273954 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0404. Min Act: -0.1700

Data Index: 3324880 (Open Web Text)

Max Activating Token Index: 845

Text #14

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0201. Min Act: -0.1700

Data Index: 737297 (Open Web Text)

Max Activating Token Index: 44

Text #15

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0261. Min Act: -0.1700

Data Index: 2942845 (Open Web Text)

Max Activating Token Index: 895

Text #16

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0127. Min Act: -0.1700

Data Index: 7247479 (Open Web Text)

Max Activating Token Index: 592

Text #17

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0059. Min Act: -0.1700

Data Index: 2814082 (Open Web Text)

Max Activating Token Index: 306

Text #18

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0160. Min Act: -0.1700

Data Index: 763343 (Open Web Text)

Max Activating Token Index: 368

Text #19

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0128. Min Act: -0.1700

Data Index: 1272704 (Open Web Text)

Max Activating Token Index: 81