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

Dataset: Open Web Text

Neuron 973 in Layer 5

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: 3.8980. Min Range: -3.8980

Max Act: 3.8980. Min Act: -0.1700

Data Index: 8174030 (Open Web Text)

Max Activating Token Index: 884

Text #1

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.8145. Min Act: -0.1700

Data Index: 6656248 (Open Web Text)

Max Activating Token Index: 392

Text #2

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7367. Min Act: -0.1700

Data Index: 8562113 (Open Web Text)

Max Activating Token Index: 88

Text #3

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7467. Min Act: -0.1700

Data Index: 6441781 (Open Web Text)

Max Activating Token Index: 402

Text #4

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7063. Min Act: -0.1700

Data Index: 935354 (Open Web Text)

Max Activating Token Index: 970

Text #5

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7093. Min Act: -0.1700

Data Index: 5710616 (Open Web Text)

Max Activating Token Index: 258

Text #6

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7224. Min Act: -0.1700

Data Index: 2451110 (Open Web Text)

Max Activating Token Index: 499

Text #7

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6959. Min Act: -0.1700

Data Index: 1929149 (Open Web Text)

Max Activating Token Index: 201

Text #8

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6771. Min Act: -0.1700

Data Index: 1030584 (Open Web Text)

Max Activating Token Index: 121

Text #9

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6764. Min Act: -0.1700

Data Index: 1246586 (Open Web Text)

Max Activating Token Index: 881

Text #10

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6627. Min Act: -0.1700

Data Index: 4407451 (Open Web Text)

Max Activating Token Index: 111

Text #11

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6782. Min Act: -0.1700

Data Index: 826648 (Open Web Text)

Max Activating Token Index: 478

Text #12

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6529. Min Act: -0.1700

Data Index: 4092773 (Open Web Text)

Max Activating Token Index: 1015

Text #13

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6864. Min Act: -0.1700

Data Index: 3375473 (Open Web Text)

Max Activating Token Index: 360

Text #14

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6674. Min Act: -0.1700

Data Index: 5012838 (Open Web Text)

Max Activating Token Index: 920

Text #15

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6188. Min Act: -0.1700

Data Index: 6546470 (Open Web Text)

Max Activating Token Index: 189

Text #16

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6557. Min Act: -0.1700

Data Index: 3169370 (Open Web Text)

Max Activating Token Index: 689

Text #17

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6513. Min Act: -0.1700

Data Index: 7140325 (Open Web Text)

Max Activating Token Index: 368

Text #18

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6127. Min Act: -0.1700

Data Index: 5039736 (Open Web Text)

Max Activating Token Index: 907

Text #19

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6124. Min Act: -0.1700

Data Index: 3422324 (Open Web Text)

Max Activating Token Index: 798