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

Dataset: Open Web Text

Neuron 3064 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: 4.7624. Min Range: -4.7624

Max Act: 4.7172. Min Act: -0.1700

Data Index: 5175704 (Open Web Text)

Max Activating Token Index: 308

Text #1

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.6900. Min Act: -0.1700

Data Index: 440882 (Open Web Text)

Max Activating Token Index: 890

Text #2

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.7521. Min Act: -0.1700

Data Index: 4286747 (Open Web Text)

Max Activating Token Index: 85

Text #3

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.7624. Min Act: -0.1700

Data Index: 2480954 (Open Web Text)

Max Activating Token Index: 481

Text #4

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.7451. Min Act: -0.1700

Data Index: 7999590 (Open Web Text)

Max Activating Token Index: 409

Text #5

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.6371. Min Act: -0.1700

Data Index: 401613 (Open Web Text)

Max Activating Token Index: 495

Text #6

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.7198. Min Act: -0.1700

Data Index: 8099004 (Open Web Text)

Max Activating Token Index: 439

Text #7

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.6709. Min Act: -0.1700

Data Index: 3185651 (Open Web Text)

Max Activating Token Index: 532

Text #8

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.6478. Min Act: -0.1700

Data Index: 1760315 (Open Web Text)

Max Activating Token Index: 817

Text #9

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.6316. Min Act: -0.1700

Data Index: 7543031 (Open Web Text)

Max Activating Token Index: 445

Text #10

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.6618. Min Act: -0.1700

Data Index: 944096 (Open Web Text)

Max Activating Token Index: 859

Text #11

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.6684. Min Act: -0.1700

Data Index: 1747001 (Open Web Text)

Max Activating Token Index: 1013

Text #12

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.6325. Min Act: -0.1700

Data Index: 3440771 (Open Web Text)

Max Activating Token Index: 596

Text #13

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.6128. Min Act: -0.1700

Data Index: 6385173 (Open Web Text)

Max Activating Token Index: 233

Text #14

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.6323. Min Act: -0.1700

Data Index: 1587376 (Open Web Text)

Max Activating Token Index: 431

Text #15

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.5894. Min Act: -0.1700

Data Index: 2895171 (Open Web Text)

Max Activating Token Index: 703

Text #16

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.5080. Min Act: -0.1700

Data Index: 7765617 (Open Web Text)

Max Activating Token Index: 542

Text #17

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.6708. Min Act: -0.1700

Data Index: 862119 (Open Web Text)

Max Activating Token Index: 403

Text #18

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.5840. Min Act: -0.1700

Data Index: 955210 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.7624. Min Range: -4.7624

Max Act: 4.5038. Min Act: -0.1700

Data Index: 7467065 (Open Web Text)

Max Activating Token Index: 716