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

Dataset: Open Web Text

Neuron 52 in Layer 5

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: 1.9699. Min Range: -1.9699

Max Act: 1.9699. Min Act: -0.1700

Data Index: 2304472 (Open Web Text)

Max Activating Token Index: 710

Text #1

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.9411. Min Act: -0.1700

Data Index: 2304473 (Open Web Text)

Max Activating Token Index: 233

Text #2

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.9079. Min Act: -0.1700

Data Index: 2685107 (Open Web Text)

Max Activating Token Index: 525

Text #3

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.8877. Min Act: -0.1700

Data Index: 130190 (Open Web Text)

Max Activating Token Index: 359

Text #4

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.8559. Min Act: -0.1700

Data Index: 6504517 (Open Web Text)

Max Activating Token Index: 989

Text #5

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.7975. Min Act: -0.1700

Data Index: 6236074 (Open Web Text)

Max Activating Token Index: 459

Text #6

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.7234. Min Act: -0.1700

Data Index: 580482 (Open Web Text)

Max Activating Token Index: 901

Text #7

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.7328. Min Act: -0.1700

Data Index: 7170914 (Open Web Text)

Max Activating Token Index: 338

Text #8

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.7367. Min Act: -0.1700

Data Index: 73783 (Open Web Text)

Max Activating Token Index: 856

Text #9

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.7626. Min Act: -0.1700

Data Index: 1707462 (Open Web Text)

Max Activating Token Index: 453

Text #10

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.7135. Min Act: -0.1700

Data Index: 7510089 (Open Web Text)

Max Activating Token Index: 220

Text #11

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.7115. Min Act: -0.1700

Data Index: 3632704 (Open Web Text)

Max Activating Token Index: 466

Text #12

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.7178. Min Act: -0.1700

Data Index: 3927074 (Open Web Text)

Max Activating Token Index: 455

Text #13

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.7083. Min Act: -0.1700

Data Index: 2280109 (Open Web Text)

Max Activating Token Index: 991

Text #14

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.6939. Min Act: -0.1700

Data Index: 5050777 (Open Web Text)

Max Activating Token Index: 666

Text #15

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.6904. Min Act: -0.1700

Data Index: 8743011 (Open Web Text)

Max Activating Token Index: 600

Text #16

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.7025. Min Act: -0.1700

Data Index: 7303222 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.6556. Min Act: -0.1700

Data Index: 3408169 (Open Web Text)

Max Activating Token Index: 881

Text #18

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.6552. Min Act: -0.1700

Data Index: 7310319 (Open Web Text)

Max Activating Token Index: 225

Text #19

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.6763. Min Act: -0.1700

Data Index: 2271901 (Open Web Text)

Max Activating Token Index: 134