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

Dataset: Open Web Text

Neuron 1471 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: 4.7375. Min Range: -4.7375

Max Act: 4.7375. Min Act: -0.1700

Data Index: 7563338 (Open Web Text)

Max Activating Token Index: 243

Text #1

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.6960. Min Act: -0.1700

Data Index: 8141475 (Open Web Text)

Max Activating Token Index: 234

Text #2

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.7033. Min Act: -0.1700

Data Index: 6394657 (Open Web Text)

Max Activating Token Index: 221

Text #3

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.6815. Min Act: -0.1700

Data Index: 3694130 (Open Web Text)

Max Activating Token Index: 640

Text #4

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.6827. Min Act: -0.1700

Data Index: 1868954 (Open Web Text)

Max Activating Token Index: 159

Text #5

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.6816. Min Act: -0.1700

Data Index: 1838028 (Open Web Text)

Max Activating Token Index: 1016

Text #6

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.6356. Min Act: -0.1700

Data Index: 2440750 (Open Web Text)

Max Activating Token Index: 730

Text #7

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.6484. Min Act: -0.1700

Data Index: 4636294 (Open Web Text)

Max Activating Token Index: 590

Text #8

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.6520. Min Act: -0.1700

Data Index: 7566086 (Open Web Text)

Max Activating Token Index: 705

Text #9

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.6090. Min Act: -0.1700

Data Index: 7127192 (Open Web Text)

Max Activating Token Index: 828

Text #10

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.6331. Min Act: -0.1700

Data Index: 4688734 (Open Web Text)

Max Activating Token Index: 778

Text #11

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.5622. Min Act: -0.1700

Data Index: 5889505 (Open Web Text)

Max Activating Token Index: 913

Text #12

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.5910. Min Act: -0.1700

Data Index: 8180324 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.5643. Min Act: -0.1700

Data Index: 6482911 (Open Web Text)

Max Activating Token Index: 351

Text #14

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.5751. Min Act: -0.1700

Data Index: 767590 (Open Web Text)

Max Activating Token Index: 273

Text #15

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.5593. Min Act: -0.1700

Data Index: 4211356 (Open Web Text)

Max Activating Token Index: 803

Text #16

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.5374. Min Act: -0.1700

Data Index: 7193508 (Open Web Text)

Max Activating Token Index: 855

Text #17

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.5144. Min Act: -0.1700

Data Index: 5969943 (Open Web Text)

Max Activating Token Index: 350

Text #18

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.4946. Min Act: -0.1700

Data Index: 6334063 (Open Web Text)

Max Activating Token Index: 386

Text #19

Max Range: 4.7375. Min Range: -4.7375

Max Act: 4.5151. Min Act: -0.1700

Data Index: 1535885 (Open Web Text)

Max Activating Token Index: 27