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

Dataset: Open Web Text

Neuron 1474 in Layer 2

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: 4.7439. Min Range: -4.7439

Max Act: 4.7423. Min Act: -0.1700

Data Index: 1718091 (Open Web Text)

Max Activating Token Index: 250

Text #1

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.7439. Min Act: -0.1700

Data Index: 6144628 (Open Web Text)

Max Activating Token Index: 521

Text #2

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.7123. Min Act: -0.1700

Data Index: 5989933 (Open Web Text)

Max Activating Token Index: 755

Text #3

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.6897. Min Act: -0.1700

Data Index: 94047 (Open Web Text)

Max Activating Token Index: 995

Text #4

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.6696. Min Act: -0.1700

Data Index: 7079329 (Open Web Text)

Max Activating Token Index: 364

Text #5

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.6908. Min Act: -0.1700

Data Index: 3093983 (Open Web Text)

Max Activating Token Index: 747

Text #6

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.6208. Min Act: -0.1700

Data Index: 913298 (Open Web Text)

Max Activating Token Index: 510

Text #7

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.6476. Min Act: -0.1700

Data Index: 6538522 (Open Web Text)

Max Activating Token Index: 387

Text #8

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.6344. Min Act: -0.1700

Data Index: 914351 (Open Web Text)

Max Activating Token Index: 217

Text #9

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.6447. Min Act: -0.1700

Data Index: 332649 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.6253. Min Act: -0.1700

Data Index: 8059947 (Open Web Text)

Max Activating Token Index: 884

Text #11

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.6423. Min Act: -0.1700

Data Index: 162569 (Open Web Text)

Max Activating Token Index: 519

Text #12

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.5985. Min Act: -0.1700

Data Index: 4482337 (Open Web Text)

Max Activating Token Index: 859

Text #13

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.5832. Min Act: -0.1700

Data Index: 4513987 (Open Web Text)

Max Activating Token Index: 646

Text #14

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.5763. Min Act: -0.1700

Data Index: 6539127 (Open Web Text)

Max Activating Token Index: 58

Text #15

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.5927. Min Act: -0.1700

Data Index: 4025665 (Open Web Text)

Max Activating Token Index: 555

Text #16

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.5511. Min Act: -0.1700

Data Index: 986068 (Open Web Text)

Max Activating Token Index: 879

Text #17

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.5618. Min Act: -0.1700

Data Index: 8407268 (Open Web Text)

Max Activating Token Index: 786

Text #18

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.5565. Min Act: -0.1700

Data Index: 300848 (Open Web Text)

Max Activating Token Index: 921

Text #19

Max Range: 4.7439. Min Range: -4.7439

Max Act: 4.5507. Min Act: -0.1700

Data Index: 3044271 (Open Web Text)

Max Activating Token Index: 300