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

Dataset: Open Web Text

Neuron 2160 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: 4.0672. Min Range: -4.0672

Max Act: 4.0672. Min Act: -0.1700

Data Index: 6491136 (Open Web Text)

Max Activating Token Index: 81

Text #1

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9745. Min Act: -0.1700

Data Index: 7949883 (Open Web Text)

Max Activating Token Index: 126

Text #2

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9999. Min Act: -0.1700

Data Index: 3695548 (Open Web Text)

Max Activating Token Index: 956

Text #3

Max Range: 4.0672. Min Range: -4.0672

Max Act: 4.0082. Min Act: -0.1700

Data Index: 4616409 (Open Web Text)

Max Activating Token Index: 210

Text #4

Max Range: 4.0672. Min Range: -4.0672

Max Act: 4.0068. Min Act: -0.1700

Data Index: 6709678 (Open Web Text)

Max Activating Token Index: 227

Text #5

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9852. Min Act: -0.1700

Data Index: 7844504 (Open Web Text)

Max Activating Token Index: 277

Text #6

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9111. Min Act: -0.1700

Data Index: 2948042 (Open Web Text)

Max Activating Token Index: 637

Text #7

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9667. Min Act: -0.1700

Data Index: 4381382 (Open Web Text)

Max Activating Token Index: 176

Text #8

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9642. Min Act: -0.1700

Data Index: 351172 (Open Web Text)

Max Activating Token Index: 415

Text #9

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9401. Min Act: -0.1700

Data Index: 1563615 (Open Web Text)

Max Activating Token Index: 496

Text #10

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9472. Min Act: -0.1700

Data Index: 4278430 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9207. Min Act: -0.1700

Data Index: 1563622 (Open Web Text)

Max Activating Token Index: 548

Text #12

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9102. Min Act: -0.1700

Data Index: 7197712 (Open Web Text)

Max Activating Token Index: 506

Text #13

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9035. Min Act: -0.1700

Data Index: 3199379 (Open Web Text)

Max Activating Token Index: 348

Text #14

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9081. Min Act: -0.1700

Data Index: 3526565 (Open Web Text)

Max Activating Token Index: 521

Text #15

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.8897. Min Act: -0.1700

Data Index: 1563626 (Open Web Text)

Max Activating Token Index: 636

Text #16

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.8971. Min Act: -0.1700

Data Index: 784621 (Open Web Text)

Max Activating Token Index: 648

Text #17

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9234. Min Act: -0.1700

Data Index: 8120108 (Open Web Text)

Max Activating Token Index: 599

Text #18

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.9232. Min Act: -0.1700

Data Index: 8565172 (Open Web Text)

Max Activating Token Index: 504

Text #19

Max Range: 4.0672. Min Range: -4.0672

Max Act: 3.8618. Min Act: -0.1700

Data Index: 8697139 (Open Web Text)

Max Activating Token Index: 209