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

Dataset: Open Web Text

Neuron 1458 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: 4.3268. Min Range: -4.3268

Max Act: 4.2558. Min Act: -0.1700

Data Index: 2431324 (Open Web Text)

Max Activating Token Index: 421

Text #1

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.1516. Min Act: -0.1700

Data Index: 6614721 (Open Web Text)

Max Activating Token Index: 495

Text #2

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.2793. Min Act: -0.1700

Data Index: 2697173 (Open Web Text)

Max Activating Token Index: 571

Text #3

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.2375. Min Act: -0.1700

Data Index: 1445705 (Open Web Text)

Max Activating Token Index: 873

Text #4

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.3268. Min Act: -0.1700

Data Index: 6051848 (Open Web Text)

Max Activating Token Index: 629

Text #5

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.2215. Min Act: -0.1700

Data Index: 6319769 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.2443. Min Act: -0.1700

Data Index: 3625692 (Open Web Text)

Max Activating Token Index: 554

Text #7

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.2026. Min Act: -0.1700

Data Index: 2431323 (Open Web Text)

Max Activating Token Index: 879

Text #8

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.1519. Min Act: -0.1700

Data Index: 6369829 (Open Web Text)

Max Activating Token Index: 496

Text #9

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.1501. Min Act: -0.1700

Data Index: 5554567 (Open Web Text)

Max Activating Token Index: 317

Text #10

Max Range: 4.3268. Min Range: -4.3268

Max Act: 3.9110. Min Act: -0.1700

Data Index: 4560346 (Open Web Text)

Max Activating Token Index: 772

Text #11

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.1159. Min Act: -0.1699

Data Index: 8289034 (Open Web Text)

Max Activating Token Index: 723

Text #12

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.0267. Min Act: -0.1700

Data Index: 2130749 (Open Web Text)

Max Activating Token Index: 719

Text #13

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.0708. Min Act: -0.1700

Data Index: 5453485 (Open Web Text)

Max Activating Token Index: 928

Text #14

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.0893. Min Act: -0.1700

Data Index: 6507935 (Open Web Text)

Max Activating Token Index: 530

Text #15

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.0506. Min Act: -0.1700

Data Index: 5195365 (Open Web Text)

Max Activating Token Index: 701

Text #16

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.1384. Min Act: -0.1700

Data Index: 4011306 (Open Web Text)

Max Activating Token Index: 98

Text #17

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.1879. Min Act: -0.1700

Data Index: 4888527 (Open Web Text)

Max Activating Token Index: 1015

Text #18

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.1100. Min Act: -0.1700

Data Index: 4044030 (Open Web Text)

Max Activating Token Index: 609

Text #19

Max Range: 4.3268. Min Range: -4.3268

Max Act: 4.1451. Min Act: -0.1700

Data Index: 7829772 (Open Web Text)

Max Activating Token Index: 458