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

Dataset: Open Web Text

Neuron 2498 in Layer 1

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: 1.8181. Min Range: -1.8181

Max Act: 1.8181. Min Act: -0.1700

Data Index: 2663109 (Open Web Text)

Max Activating Token Index: 665

Text #1

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7860. Min Act: -0.1700

Data Index: 5045991 (Open Web Text)

Max Activating Token Index: 143

Text #2

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7873. Min Act: -0.1700

Data Index: 4162929 (Open Web Text)

Max Activating Token Index: 579

Text #3

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7893. Min Act: -0.1700

Data Index: 5072966 (Open Web Text)

Max Activating Token Index: 88

Text #4

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7623. Min Act: -0.1700

Data Index: 1185066 (Open Web Text)

Max Activating Token Index: 629

Text #5

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7649. Min Act: -0.1700

Data Index: 2489265 (Open Web Text)

Max Activating Token Index: 564

Text #6

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7708. Min Act: -0.1700

Data Index: 4515443 (Open Web Text)

Max Activating Token Index: 150

Text #7

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7587. Min Act: -0.1699

Data Index: 6753860 (Open Web Text)

Max Activating Token Index: 411

Text #8

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7648. Min Act: -0.1700

Data Index: 5049109 (Open Web Text)

Max Activating Token Index: 757

Text #9

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7449. Min Act: -0.1700

Data Index: 2135705 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7512. Min Act: -0.1700

Data Index: 2378314 (Open Web Text)

Max Activating Token Index: 563

Text #11

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7587. Min Act: -0.1700

Data Index: 5790455 (Open Web Text)

Max Activating Token Index: 424

Text #12

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7432. Min Act: -0.1700

Data Index: 7064890 (Open Web Text)

Max Activating Token Index: 264

Text #13

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7400. Min Act: -0.1700

Data Index: 1285430 (Open Web Text)

Max Activating Token Index: 570

Text #14

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7371. Min Act: -0.1700

Data Index: 3599921 (Open Web Text)

Max Activating Token Index: 973

Text #15

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7450. Min Act: -0.1700

Data Index: 5208321 (Open Web Text)

Max Activating Token Index: 180

Text #16

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7361. Min Act: -0.1700

Data Index: 7866621 (Open Web Text)

Max Activating Token Index: 546

Text #17

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7373. Min Act: -0.1700

Data Index: 4465426 (Open Web Text)

Max Activating Token Index: 223

Text #18

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7489. Min Act: -0.1700

Data Index: 8158178 (Open Web Text)

Max Activating Token Index: 1006

Text #19

Max Range: 1.8181. Min Range: -1.8181

Max Act: 1.7386. Min Act: -0.1700

Data Index: 587833 (Open Web Text)

Max Activating Token Index: 811