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

Dataset: Open Web Text

Neuron 1298 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: 3.3857. Min Range: -3.3857

Max Act: 3.3857. Min Act: -0.1700

Data Index: 2791880 (Open Web Text)

Max Activating Token Index: 584

Text #1

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.3457. Min Act: -0.1700

Data Index: 8747388 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.3403. Min Act: -0.1700

Data Index: 1460549 (Open Web Text)

Max Activating Token Index: 448

Text #3

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2996. Min Act: -0.1700

Data Index: 4341063 (Open Web Text)

Max Activating Token Index: 511

Text #4

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2922. Min Act: -0.1700

Data Index: 664613 (Open Web Text)

Max Activating Token Index: 203

Text #5

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.3236. Min Act: -0.1700

Data Index: 3827627 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2924. Min Act: -0.1700

Data Index: 1947812 (Open Web Text)

Max Activating Token Index: 775

Text #7

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2987. Min Act: -0.1700

Data Index: 1802158 (Open Web Text)

Max Activating Token Index: 487

Text #8

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2781. Min Act: -0.1700

Data Index: 2355098 (Open Web Text)

Max Activating Token Index: 593

Text #9

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2611. Min Act: -0.1700

Data Index: 4447486 (Open Web Text)

Max Activating Token Index: 33

Text #10

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2440. Min Act: -0.1700

Data Index: 485427 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2335. Min Act: -0.1700

Data Index: 1839841 (Open Web Text)

Max Activating Token Index: 765

Text #12

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2354. Min Act: -0.1700

Data Index: 7900341 (Open Web Text)

Max Activating Token Index: 705

Text #13

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2398. Min Act: -0.1700

Data Index: 6239785 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2566. Min Act: -0.1700

Data Index: 7840676 (Open Web Text)

Max Activating Token Index: 283

Text #15

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2423. Min Act: -0.1700

Data Index: 2251537 (Open Web Text)

Max Activating Token Index: 584

Text #16

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2206. Min Act: -0.1700

Data Index: 8051002 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2193. Min Act: -0.1700

Data Index: 6809831 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2459. Min Act: -0.1700

Data Index: 3937132 (Open Web Text)

Max Activating Token Index: 124

Text #19

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2442. Min Act: -0.1700

Data Index: 7007605 (Open Web Text)

Max Activating Token Index: 643