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

Dataset: Open Web Text

Neuron 288 in Layer 0

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: 3.4041. Min Range: -3.4041

Max Act: 3.4041. Min Act: -0.1700

Data Index: 3631146 (Open Web Text)

Max Activating Token Index: 726

Text #1

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.2776. Min Act: -0.1700

Data Index: 2978203 (Open Web Text)

Max Activating Token Index: 630

Text #2

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.2634. Min Act: -0.1700

Data Index: 7672091 (Open Web Text)

Max Activating Token Index: 760

Text #3

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.2676. Min Act: -0.1700

Data Index: 4283442 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.2570. Min Act: -0.1700

Data Index: 5335016 (Open Web Text)

Max Activating Token Index: 64

Text #5

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.2594. Min Act: -0.1700

Data Index: 8290788 (Open Web Text)

Max Activating Token Index: 665

Text #6

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.2475. Min Act: -0.1700

Data Index: 8594046 (Open Web Text)

Max Activating Token Index: 943

Text #7

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.2234. Min Act: -0.1700

Data Index: 7372166 (Open Web Text)

Max Activating Token Index: 116

Text #8

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.2449. Min Act: -0.1700

Data Index: 7260688 (Open Web Text)

Max Activating Token Index: 60

Text #9

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.2138. Min Act: -0.1700

Data Index: 8145192 (Open Web Text)

Max Activating Token Index: 565

Text #10

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.2126. Min Act: -0.1700

Data Index: 6043215 (Open Web Text)

Max Activating Token Index: 678

Text #11

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.2123. Min Act: -0.1700

Data Index: 8514021 (Open Web Text)

Max Activating Token Index: 868

Text #12

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.2010. Min Act: -0.1700

Data Index: 5221462 (Open Web Text)

Max Activating Token Index: 395

Text #13

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.1996. Min Act: -0.1700

Data Index: 6096456 (Open Web Text)

Max Activating Token Index: 452

Text #14

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.1956. Min Act: -0.1700

Data Index: 1871047 (Open Web Text)

Max Activating Token Index: 224

Text #15

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.1922. Min Act: -0.1700

Data Index: 8656759 (Open Web Text)

Max Activating Token Index: 96

Text #16

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.1868. Min Act: -0.1700

Data Index: 8640600 (Open Web Text)

Max Activating Token Index: 586

Text #17

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.1857. Min Act: -0.1700

Data Index: 7026695 (Open Web Text)

Max Activating Token Index: 406

Text #18

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.1968. Min Act: -0.1700

Data Index: 684012 (Open Web Text)

Max Activating Token Index: 34

Text #19

Max Range: 3.4041. Min Range: -3.4041

Max Act: 3.1647. Min Act: -0.1700

Data Index: 2125086 (Open Web Text)

Max Activating Token Index: 356