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

Dataset: Open Web Text

Neuron 2034 in Layer 3

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: 3.1158. Min Range: -3.1158

Max Act: 3.1158. Min Act: -0.1700

Data Index: 5413367 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 3.1158. Min Range: -3.1158

Max Act: 3.0774. Min Act: -0.1700

Data Index: 4721155 (Open Web Text)

Max Activating Token Index: 34

Text #2

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9950. Min Act: -0.1700

Data Index: 1984157 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 3.1158. Min Range: -3.1158

Max Act: 3.0187. Min Act: -0.1700

Data Index: 6438388 (Open Web Text)

Max Activating Token Index: 757

Text #4

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9929. Min Act: -0.1700

Data Index: 192333 (Open Web Text)

Max Activating Token Index: 505

Text #5

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9806. Min Act: -0.1700

Data Index: 3599291 (Open Web Text)

Max Activating Token Index: 659

Text #6

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9751. Min Act: -0.1700

Data Index: 752992 (Open Web Text)

Max Activating Token Index: 553

Text #7

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9887. Min Act: -0.1700

Data Index: 1581344 (Open Web Text)

Max Activating Token Index: 199

Text #8

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9658. Min Act: -0.1700

Data Index: 4957303 (Open Web Text)

Max Activating Token Index: 980

Text #9

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9637. Min Act: -0.1700

Data Index: 465335 (Open Web Text)

Max Activating Token Index: 246

Text #10

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9621. Min Act: -0.1700

Data Index: 7253742 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9656. Min Act: -0.1700

Data Index: 6774251 (Open Web Text)

Max Activating Token Index: 985

Text #12

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9585. Min Act: -0.1700

Data Index: 750835 (Open Web Text)

Max Activating Token Index: 491

Text #13

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9550. Min Act: -0.1700

Data Index: 913003 (Open Web Text)

Max Activating Token Index: 808

Text #14

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9216. Min Act: -0.1700

Data Index: 3665884 (Open Web Text)

Max Activating Token Index: 390

Text #15

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9241. Min Act: -0.1700

Data Index: 2968242 (Open Web Text)

Max Activating Token Index: 710

Text #16

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9474. Min Act: -0.1700

Data Index: 8720482 (Open Web Text)

Max Activating Token Index: 474

Text #17

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9101. Min Act: -0.1700

Data Index: 6018196 (Open Web Text)

Max Activating Token Index: 23

Text #18

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9055. Min Act: -0.1700

Data Index: 1043596 (Open Web Text)

Max Activating Token Index: 943

Text #19

Max Range: 3.1158. Min Range: -3.1158

Max Act: 2.9258. Min Act: -0.1700

Data Index: 4871653 (Open Web Text)

Max Activating Token Index: 12