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

Dataset: Open Web Text

Neuron 1021 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: 3.0992. Min Range: -3.0992

Max Act: 3.0992. Min Act: -0.1700

Data Index: 29270 (Open Web Text)

Max Activating Token Index: 24

Text #1

Max Range: 3.0992. Min Range: -3.0992

Max Act: 3.0619. Min Act: -0.1700

Data Index: 3725794 (Open Web Text)

Max Activating Token Index: 687

Text #2

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.9784. Min Act: -0.1700

Data Index: 2906331 (Open Web Text)

Max Activating Token Index: 72

Text #3

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.9435. Min Act: -0.1700

Data Index: 3517472 (Open Web Text)

Max Activating Token Index: 100

Text #4

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.9351. Min Act: -0.1700

Data Index: 1999265 (Open Web Text)

Max Activating Token Index: 573

Text #5

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.9145. Min Act: -0.1700

Data Index: 1285216 (Open Web Text)

Max Activating Token Index: 109

Text #6

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.8701. Min Act: -0.1700

Data Index: 1976866 (Open Web Text)

Max Activating Token Index: 34

Text #7

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.8501. Min Act: -0.1700

Data Index: 1032114 (Open Web Text)

Max Activating Token Index: 158

Text #8

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.8635. Min Act: -0.1700

Data Index: 421260 (Open Web Text)

Max Activating Token Index: 556

Text #9

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.8225. Min Act: -0.1700

Data Index: 843371 (Open Web Text)

Max Activating Token Index: 1008

Text #10

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.8738. Min Act: -0.1700

Data Index: 3838369 (Open Web Text)

Max Activating Token Index: 33

Text #11

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.8172. Min Act: -0.1700

Data Index: 8103636 (Open Web Text)

Max Activating Token Index: 912

Text #12

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.8123. Min Act: -0.1700

Data Index: 5512211 (Open Web Text)

Max Activating Token Index: 278

Text #13

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.8336. Min Act: -0.1700

Data Index: 2200625 (Open Web Text)

Max Activating Token Index: 56

Text #14

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.8127. Min Act: -0.1700

Data Index: 7469945 (Open Web Text)

Max Activating Token Index: 220

Text #15

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.8079. Min Act: -0.1700

Data Index: 6711487 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.7908. Min Act: -0.1700

Data Index: 2007082 (Open Web Text)

Max Activating Token Index: 811

Text #17

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.8090. Min Act: -0.1700

Data Index: 710328 (Open Web Text)

Max Activating Token Index: 456

Text #18

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.8136. Min Act: -0.1700

Data Index: 382677 (Open Web Text)

Max Activating Token Index: 107

Text #19

Max Range: 3.0992. Min Range: -3.0992

Max Act: 2.8312. Min Act: -0.1700

Data Index: 7736441 (Open Web Text)

Max Activating Token Index: 504