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

Dataset: Open Web Text

Neuron 2391 in Layer 6

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: 4.9180. Min Range: -4.9180

Max Act: 4.8950. Min Act: -0.1700

Data Index: 260712 (Open Web Text)

Max Activating Token Index: 606

Text #1

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.9180. Min Act: -0.1700

Data Index: 2825325 (Open Web Text)

Max Activating Token Index: 303

Text #2

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7659. Min Act: -0.1700

Data Index: 5425425 (Open Web Text)

Max Activating Token Index: 833

Text #3

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7590. Min Act: -0.1700

Data Index: 2510163 (Open Web Text)

Max Activating Token Index: 206

Text #4

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7651. Min Act: -0.1700

Data Index: 33066 (Open Web Text)

Max Activating Token Index: 386

Text #5

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7467. Min Act: -0.1700

Data Index: 8042066 (Open Web Text)

Max Activating Token Index: 865

Text #6

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7699. Min Act: -0.1700

Data Index: 1255535 (Open Web Text)

Max Activating Token Index: 973

Text #7

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7657. Min Act: -0.1700

Data Index: 554739 (Open Web Text)

Max Activating Token Index: 852

Text #8

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7321. Min Act: -0.1700

Data Index: 6036135 (Open Web Text)

Max Activating Token Index: 340

Text #9

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7483. Min Act: -0.1700

Data Index: 5437579 (Open Web Text)

Max Activating Token Index: 920

Text #10

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7146. Min Act: -0.1700

Data Index: 5911077 (Open Web Text)

Max Activating Token Index: 233

Text #11

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7312. Min Act: -0.1700

Data Index: 7947724 (Open Web Text)

Max Activating Token Index: 396

Text #12

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.6960. Min Act: -0.1700

Data Index: 2863758 (Open Web Text)

Max Activating Token Index: 734

Text #13

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.6987. Min Act: -0.1700

Data Index: 8476077 (Open Web Text)

Max Activating Token Index: 227

Text #14

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.6736. Min Act: -0.1700

Data Index: 1766763 (Open Web Text)

Max Activating Token Index: 527

Text #15

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7178. Min Act: -0.1700

Data Index: 7408858 (Open Web Text)

Max Activating Token Index: 754

Text #16

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7075. Min Act: -0.1700

Data Index: 7358102 (Open Web Text)

Max Activating Token Index: 181

Text #17

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7031. Min Act: -0.1700

Data Index: 7007240 (Open Web Text)

Max Activating Token Index: 471

Text #18

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.6956. Min Act: -0.1700

Data Index: 6146453 (Open Web Text)

Max Activating Token Index: 337

Text #19

Max Range: 4.9180. Min Range: -4.9180

Max Act: 4.7028. Min Act: -0.1700

Data Index: 3867954 (Open Web Text)

Max Activating Token Index: 729