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

Dataset: Open Web Text

Neuron 380 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: 2.9191. Min Range: -2.9191

Max Act: 2.9191. Min Act: -0.1700

Data Index: 3500344 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.8732. Min Act: -0.1700

Data Index: 410297 (Open Web Text)

Max Activating Token Index: 612

Text #2

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.8200. Min Act: -0.1700

Data Index: 3968572 (Open Web Text)

Max Activating Token Index: 954

Text #3

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.8026. Min Act: -0.1700

Data Index: 2513159 (Open Web Text)

Max Activating Token Index: 608

Text #4

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.8006. Min Act: -0.1700

Data Index: 7844298 (Open Web Text)

Max Activating Token Index: 317

Text #5

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.7698. Min Act: -0.1700

Data Index: 7994414 (Open Web Text)

Max Activating Token Index: 472

Text #6

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.7578. Min Act: -0.1700

Data Index: 5725654 (Open Web Text)

Max Activating Token Index: 482

Text #7

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.7590. Min Act: -0.1700

Data Index: 410298 (Open Web Text)

Max Activating Token Index: 282

Text #8

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.7531. Min Act: -0.1700

Data Index: 100100 (Open Web Text)

Max Activating Token Index: 447

Text #9

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.7322. Min Act: -0.1700

Data Index: 6319097 (Open Web Text)

Max Activating Token Index: 832

Text #10

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.7502. Min Act: -0.1700

Data Index: 3627553 (Open Web Text)

Max Activating Token Index: 742

Text #11

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.7343. Min Act: -0.1700

Data Index: 7767039 (Open Web Text)

Max Activating Token Index: 607

Text #12

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.7268. Min Act: -0.1700

Data Index: 4213190 (Open Web Text)

Max Activating Token Index: 1003

Text #13

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.7112. Min Act: -0.1700

Data Index: 8682099 (Open Web Text)

Max Activating Token Index: 705

Text #14

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.7026. Min Act: -0.1700

Data Index: 3278384 (Open Web Text)

Max Activating Token Index: 731

Text #15

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.7029. Min Act: -0.1700

Data Index: 6790509 (Open Web Text)

Max Activating Token Index: 765

Text #16

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.6988. Min Act: -0.1700

Data Index: 6365341 (Open Web Text)

Max Activating Token Index: 428

Text #17

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.7195. Min Act: -0.1700

Data Index: 2862041 (Open Web Text)

Max Activating Token Index: 91

Text #18

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.6919. Min Act: -0.1700

Data Index: 5856656 (Open Web Text)

Max Activating Token Index: 792

Text #19

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.6782. Min Act: -0.1700

Data Index: 6248460 (Open Web Text)

Max Activating Token Index: 715