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

Dataset: Open Web Text

Neuron 2538 in Layer 1

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: 1.8830. Min Range: -1.8830

Max Act: 1.8830. Min Act: -0.1700

Data Index: 3133304 (Open Web Text)

Max Activating Token Index: 767

Text #1

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8396. Min Act: -0.1700

Data Index: 4143329 (Open Web Text)

Max Activating Token Index: 164

Text #2

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8163. Min Act: -0.1700

Data Index: 2487276 (Open Web Text)

Max Activating Token Index: 763

Text #3

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8019. Min Act: -0.1700

Data Index: 8335220 (Open Web Text)

Max Activating Token Index: 282

Text #4

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8002. Min Act: -0.1700

Data Index: 916039 (Open Web Text)

Max Activating Token Index: 37

Text #5

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7836. Min Act: -0.1700

Data Index: 6389964 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7903. Min Act: -0.1700

Data Index: 5130698 (Open Web Text)

Max Activating Token Index: 135

Text #7

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7885. Min Act: -0.1700

Data Index: 2099459 (Open Web Text)

Max Activating Token Index: 647

Text #8

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7808. Min Act: -0.1700

Data Index: 3544577 (Open Web Text)

Max Activating Token Index: 32

Text #9

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7645. Min Act: -0.1700

Data Index: 1220877 (Open Web Text)

Max Activating Token Index: 163

Text #10

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7740. Min Act: -0.1697

Data Index: 3083150 (Open Web Text)

Max Activating Token Index: 569

Text #11

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7748. Min Act: -0.1700

Data Index: 3545345 (Open Web Text)

Max Activating Token Index: 158

Text #12

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7739. Min Act: -0.1696

Data Index: 7593503 (Open Web Text)

Max Activating Token Index: 674

Text #13

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7603. Min Act: -0.1700

Data Index: 4143328 (Open Web Text)

Max Activating Token Index: 732

Text #14

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7531. Min Act: -0.1700

Data Index: 7126372 (Open Web Text)

Max Activating Token Index: 208

Text #15

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7495. Min Act: -0.1700

Data Index: 2751617 (Open Web Text)

Max Activating Token Index: 695

Text #16

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7469. Min Act: -0.1700

Data Index: 8076760 (Open Web Text)

Max Activating Token Index: 114

Text #17

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7403. Min Act: -0.1700

Data Index: 4276464 (Open Web Text)

Max Activating Token Index: 654

Text #18

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7384. Min Act: -0.1700

Data Index: 408928 (Open Web Text)

Max Activating Token Index: 644

Text #19

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7249. Min Act: -0.1699

Data Index: 6364648 (Open Web Text)

Max Activating Token Index: 767