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

Dataset: Open Web Text

Neuron 478 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: 4.0821. Min Range: -4.0821

Max Act: 4.0821. Min Act: -0.1700

Data Index: 2672736 (Open Web Text)

Max Activating Token Index: 178

Text #1

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.8000. Min Act: -0.1700

Data Index: 1885533 (Open Web Text)

Max Activating Token Index: 523

Text #2

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.8006. Min Act: -0.1700

Data Index: 2470050 (Open Web Text)

Max Activating Token Index: 459

Text #3

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.7319. Min Act: -0.1700

Data Index: 3191782 (Open Web Text)

Max Activating Token Index: 376

Text #4

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.7257. Min Act: -0.1700

Data Index: 4755283 (Open Web Text)

Max Activating Token Index: 681

Text #5

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6810. Min Act: -0.1700

Data Index: 6741134 (Open Web Text)

Max Activating Token Index: 170

Text #6

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6663. Min Act: -0.1700

Data Index: 5508042 (Open Web Text)

Max Activating Token Index: 539

Text #7

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6611. Min Act: -0.1700

Data Index: 4388614 (Open Web Text)

Max Activating Token Index: 649

Text #8

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6643. Min Act: -0.1700

Data Index: 1676255 (Open Web Text)

Max Activating Token Index: 681

Text #9

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6666. Min Act: -0.1700

Data Index: 7662341 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6526. Min Act: -0.1700

Data Index: 2041366 (Open Web Text)

Max Activating Token Index: 407

Text #11

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6638. Min Act: -0.1700

Data Index: 8645290 (Open Web Text)

Max Activating Token Index: 566

Text #12

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6338. Min Act: -0.1700

Data Index: 4351980 (Open Web Text)

Max Activating Token Index: 881

Text #13

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6264. Min Act: -0.1700

Data Index: 1413893 (Open Web Text)

Max Activating Token Index: 774

Text #14

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6409. Min Act: -0.1700

Data Index: 646088 (Open Web Text)

Max Activating Token Index: 116

Text #15

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6169. Min Act: -0.1700

Data Index: 7221880 (Open Web Text)

Max Activating Token Index: 488

Text #16

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6331. Min Act: -0.1700

Data Index: 2722425 (Open Web Text)

Max Activating Token Index: 492

Text #17

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6208. Min Act: -0.1700

Data Index: 4204453 (Open Web Text)

Max Activating Token Index: 282

Text #18

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6309. Min Act: -0.1700

Data Index: 1819328 (Open Web Text)

Max Activating Token Index: 434

Text #19

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.6221. Min Act: -0.1700

Data Index: 5006237 (Open Web Text)

Max Activating Token Index: 2