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

Dataset: Open Web Text

Neuron 2162 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: 4.2569. Min Range: -4.2569

Max Act: 4.2340. Min Act: -0.1700

Data Index: 6828521 (Open Web Text)

Max Activating Token Index: 408

Text #1

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.2569. Min Act: -0.1700

Data Index: 8156567 (Open Web Text)

Max Activating Token Index: 250

Text #2

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.2428. Min Act: -0.1700

Data Index: 6086564 (Open Web Text)

Max Activating Token Index: 134

Text #3

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.2519. Min Act: -0.1700

Data Index: 6006619 (Open Web Text)

Max Activating Token Index: 56

Text #4

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.2469. Min Act: -0.1700

Data Index: 2374580 (Open Web Text)

Max Activating Token Index: 816

Text #5

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.2187. Min Act: -0.1700

Data Index: 2392489 (Open Web Text)

Max Activating Token Index: 493

Text #6

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.1838. Min Act: -0.1700

Data Index: 8721466 (Open Web Text)

Max Activating Token Index: 749

Text #7

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.1939. Min Act: -0.1700

Data Index: 6367862 (Open Web Text)

Max Activating Token Index: 346

Text #8

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.1747. Min Act: -0.1700

Data Index: 8347265 (Open Web Text)

Max Activating Token Index: 63

Text #9

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.1679. Min Act: -0.1700

Data Index: 7309585 (Open Web Text)

Max Activating Token Index: 470

Text #10

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.2066. Min Act: -0.1700

Data Index: 7077019 (Open Web Text)

Max Activating Token Index: 608

Text #11

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.1831. Min Act: -0.1700

Data Index: 5114955 (Open Web Text)

Max Activating Token Index: 765

Text #12

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.1976. Min Act: -0.1700

Data Index: 5107220 (Open Web Text)

Max Activating Token Index: 895

Text #13

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.1731. Min Act: -0.1700

Data Index: 231887 (Open Web Text)

Max Activating Token Index: 370

Text #14

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.1326. Min Act: -0.1700

Data Index: 7115597 (Open Web Text)

Max Activating Token Index: 962

Text #15

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.1493. Min Act: -0.1700

Data Index: 2497113 (Open Web Text)

Max Activating Token Index: 767

Text #16

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.1297. Min Act: -0.1700

Data Index: 2598517 (Open Web Text)

Max Activating Token Index: 94

Text #17

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.1501. Min Act: -0.1700

Data Index: 8398129 (Open Web Text)

Max Activating Token Index: 1021

Text #18

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.1577. Min Act: -0.1700

Data Index: 8563748 (Open Web Text)

Max Activating Token Index: 42

Text #19

Max Range: 4.2569. Min Range: -4.2569

Max Act: 4.1570. Min Act: -0.1700

Data Index: 4949530 (Open Web Text)

Max Activating Token Index: 49