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

Dataset: Open Web Text

Neuron 2102 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: 3.6333. Min Range: -3.6333

Max Act: 3.6333. Min Act: -0.1700

Data Index: 1496560 (Open Web Text)

Max Activating Token Index: 995

Text #1

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.6163. Min Act: -0.1700

Data Index: 5556417 (Open Web Text)

Max Activating Token Index: 432

Text #2

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.6155. Min Act: -0.1700

Data Index: 1684032 (Open Web Text)

Max Activating Token Index: 894

Text #3

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5747. Min Act: -0.1700

Data Index: 6433805 (Open Web Text)

Max Activating Token Index: 435

Text #4

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5735. Min Act: -0.1700

Data Index: 6533601 (Open Web Text)

Max Activating Token Index: 1006

Text #5

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.6057. Min Act: -0.1700

Data Index: 7627015 (Open Web Text)

Max Activating Token Index: 936

Text #6

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5993. Min Act: -0.1700

Data Index: 2428695 (Open Web Text)

Max Activating Token Index: 462

Text #7

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.6154. Min Act: -0.1700

Data Index: 2659990 (Open Web Text)

Max Activating Token Index: 448

Text #8

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5864. Min Act: -0.1700

Data Index: 1644559 (Open Web Text)

Max Activating Token Index: 595

Text #9

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5814. Min Act: -0.1700

Data Index: 2813357 (Open Web Text)

Max Activating Token Index: 867

Text #10

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5522. Min Act: -0.1700

Data Index: 3071259 (Open Web Text)

Max Activating Token Index: 887

Text #11

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5302. Min Act: -0.1700

Data Index: 2897738 (Open Web Text)

Max Activating Token Index: 925

Text #12

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5793. Min Act: -0.1700

Data Index: 205599 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5794. Min Act: -0.1700

Data Index: 2675290 (Open Web Text)

Max Activating Token Index: 941

Text #14

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5970. Min Act: -0.1700

Data Index: 1140205 (Open Web Text)

Max Activating Token Index: 474

Text #15

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5324. Min Act: -0.1700

Data Index: 1684033 (Open Web Text)

Max Activating Token Index: 894

Text #16

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5512. Min Act: -0.1700

Data Index: 1079053 (Open Web Text)

Max Activating Token Index: 801

Text #17

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5522. Min Act: -0.1700

Data Index: 922781 (Open Web Text)

Max Activating Token Index: 933

Text #18

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5430. Min Act: -0.1700

Data Index: 2659987 (Open Web Text)

Max Activating Token Index: 1019

Text #19

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5843. Min Act: -0.1700

Data Index: 2402233 (Open Web Text)

Max Activating Token Index: 418