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

Dataset: Open Web Text

Neuron 1566 in Layer 4

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: 4.7362. Min Range: -4.7362

Max Act: 4.7362. Min Act: -0.1700

Data Index: 1526384 (Open Web Text)

Max Activating Token Index: 837

Text #1

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6794. Min Act: -0.1700

Data Index: 1568012 (Open Web Text)

Max Activating Token Index: 806

Text #2

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6930. Min Act: -0.1700

Data Index: 1682729 (Open Web Text)

Max Activating Token Index: 916

Text #3

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6870. Min Act: -0.1700

Data Index: 4838816 (Open Web Text)

Max Activating Token Index: 856

Text #4

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6707. Min Act: -0.1700

Data Index: 1327189 (Open Web Text)

Max Activating Token Index: 909

Text #5

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6842. Min Act: -0.1700

Data Index: 415708 (Open Web Text)

Max Activating Token Index: 715

Text #6

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6645. Min Act: -0.1700

Data Index: 8634846 (Open Web Text)

Max Activating Token Index: 856

Text #7

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6443. Min Act: -0.1700

Data Index: 8334038 (Open Web Text)

Max Activating Token Index: 1001

Text #8

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6703. Min Act: -0.1700

Data Index: 7028170 (Open Web Text)

Max Activating Token Index: 996

Text #9

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6687. Min Act: -0.1700

Data Index: 6008064 (Open Web Text)

Max Activating Token Index: 877

Text #10

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6458. Min Act: -0.1700

Data Index: 5547351 (Open Web Text)

Max Activating Token Index: 830

Text #11

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6473. Min Act: -0.1700

Data Index: 4610866 (Open Web Text)

Max Activating Token Index: 887

Text #12

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6601. Min Act: -0.1700

Data Index: 4472766 (Open Web Text)

Max Activating Token Index: 790

Text #13

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6560. Min Act: -0.1700

Data Index: 2976526 (Open Web Text)

Max Activating Token Index: 282

Text #14

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6564. Min Act: -0.1700

Data Index: 740242 (Open Web Text)

Max Activating Token Index: 839

Text #15

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6568. Min Act: -0.1700

Data Index: 2867262 (Open Web Text)

Max Activating Token Index: 954

Text #16

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6450. Min Act: -0.1700

Data Index: 2686688 (Open Web Text)

Max Activating Token Index: 794

Text #17

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6476. Min Act: -0.1700

Data Index: 2475783 (Open Web Text)

Max Activating Token Index: 870

Text #18

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6358. Min Act: -0.1700

Data Index: 1725100 (Open Web Text)

Max Activating Token Index: 870

Text #19

Max Range: 4.7362. Min Range: -4.7362

Max Act: 4.6621. Min Act: -0.1700

Data Index: 178638 (Open Web Text)

Max Activating Token Index: 902