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

Dataset: Open Web Text

Neuron 1805 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: 4.3665. Min Range: -4.3665

Max Act: 4.3665. Min Act: -0.1700

Data Index: 7984619 (Open Web Text)

Max Activating Token Index: 394

Text #1

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.2637. Min Act: -0.1700

Data Index: 5392809 (Open Web Text)

Max Activating Token Index: 575

Text #2

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.2309. Min Act: -0.1700

Data Index: 2373344 (Open Web Text)

Max Activating Token Index: 97

Text #3

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.2210. Min Act: -0.1700

Data Index: 8657698 (Open Web Text)

Max Activating Token Index: 802

Text #4

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1780. Min Act: -0.1700

Data Index: 1826500 (Open Web Text)

Max Activating Token Index: 718

Text #5

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1780. Min Act: -0.1700

Data Index: 3617273 (Open Web Text)

Max Activating Token Index: 581

Text #6

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1569. Min Act: -0.1700

Data Index: 2590962 (Open Web Text)

Max Activating Token Index: 855

Text #7

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1937. Min Act: -0.1700

Data Index: 8227930 (Open Web Text)

Max Activating Token Index: 109

Text #8

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1974. Min Act: -0.1700

Data Index: 2703055 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1972. Min Act: -0.1700

Data Index: 3076036 (Open Web Text)

Max Activating Token Index: 313

Text #10

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1944. Min Act: -0.1700

Data Index: 7818752 (Open Web Text)

Max Activating Token Index: 194

Text #11

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1761. Min Act: -0.1700

Data Index: 3597558 (Open Web Text)

Max Activating Token Index: 26

Text #12

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1779. Min Act: -0.1700

Data Index: 5533471 (Open Web Text)

Max Activating Token Index: 590

Text #13

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1651. Min Act: -0.1700

Data Index: 5859361 (Open Web Text)

Max Activating Token Index: 367

Text #14

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1495. Min Act: -0.1700

Data Index: 1486502 (Open Web Text)

Max Activating Token Index: 664

Text #15

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1241. Min Act: -0.1700

Data Index: 1352574 (Open Web Text)

Max Activating Token Index: 107

Text #16

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1427. Min Act: -0.1700

Data Index: 3064150 (Open Web Text)

Max Activating Token Index: 252

Text #17

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1281. Min Act: -0.1700

Data Index: 1997821 (Open Web Text)

Max Activating Token Index: 991

Text #18

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1349. Min Act: -0.1700

Data Index: 1980705 (Open Web Text)

Max Activating Token Index: 291

Text #19

Max Range: 4.3665. Min Range: -4.3665

Max Act: 4.1504. Min Act: -0.1700

Data Index: 3513695 (Open Web Text)

Max Activating Token Index: 933