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

Dataset: Open Web Text

Neuron 2673 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: 4.7395. Min Range: -4.7395

Max Act: 4.7395. Min Act: -0.1700

Data Index: 7895424 (Open Web Text)

Max Activating Token Index: 158

Text #1

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.6783. Min Act: -0.1700

Data Index: 2694723 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.6508. Min Act: -0.1700

Data Index: 911677 (Open Web Text)

Max Activating Token Index: 82

Text #3

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.5049. Min Act: -0.1700

Data Index: 3410107 (Open Web Text)

Max Activating Token Index: 63

Text #4

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.4768. Min Act: -0.1700

Data Index: 1612007 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.4671. Min Act: -0.1700

Data Index: 6751696 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.4509. Min Act: -0.1700

Data Index: 753713 (Open Web Text)

Max Activating Token Index: 48

Text #7

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.4222. Min Act: -0.1700

Data Index: 8758406 (Open Web Text)

Max Activating Token Index: 30

Text #8

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.3997. Min Act: -0.1700

Data Index: 3833938 (Open Web Text)

Max Activating Token Index: 179

Text #9

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.3493. Min Act: -0.1700

Data Index: 25185 (Open Web Text)

Max Activating Token Index: 350

Text #10

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.3663. Min Act: -0.1700

Data Index: 5496053 (Open Web Text)

Max Activating Token Index: 646

Text #11

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.3504. Min Act: -0.1700

Data Index: 5957413 (Open Web Text)

Max Activating Token Index: 800

Text #12

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.3058. Min Act: -0.1700

Data Index: 5173004 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.3367. Min Act: -0.1700

Data Index: 6656991 (Open Web Text)

Max Activating Token Index: 560

Text #14

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.3326. Min Act: -0.1700

Data Index: 3186661 (Open Web Text)

Max Activating Token Index: 101

Text #15

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.3399. Min Act: -0.1700

Data Index: 3640121 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.3227. Min Act: -0.1700

Data Index: 6876443 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.3211. Min Act: -0.1700

Data Index: 1586131 (Open Web Text)

Max Activating Token Index: 642

Text #18

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.3122. Min Act: -0.1700

Data Index: 4122140 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 4.7395. Min Range: -4.7395

Max Act: 4.3011. Min Act: -0.1700

Data Index: 7184281 (Open Web Text)

Max Activating Token Index: 22