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

Dataset: Open Web Text

Neuron 2198 in Layer 1

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: 2.1925. Min Range: -2.1925

Max Act: 2.1925. Min Act: -0.1700

Data Index: 1882656 (Open Web Text)

Max Activating Token Index: 32

Text #1

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.1768. Min Act: -0.1700

Data Index: 1923909 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0981. Min Act: -0.1700

Data Index: 3978249 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0813. Min Act: -0.1700

Data Index: 3740678 (Open Web Text)

Max Activating Token Index: 40

Text #4

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0568. Min Act: -0.1700

Data Index: 2787497 (Open Web Text)

Max Activating Token Index: 30

Text #5

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0556. Min Act: -0.1700

Data Index: 4913517 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0565. Min Act: -0.1700

Data Index: 588084 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0634. Min Act: -0.1700

Data Index: 7171304 (Open Web Text)

Max Activating Token Index: 47

Text #8

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0701. Min Act: -0.1700

Data Index: 670146 (Open Web Text)

Max Activating Token Index: 604

Text #9

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0442. Min Act: -0.1700

Data Index: 5319183 (Open Web Text)

Max Activating Token Index: 231

Text #10

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0386. Min Act: -0.1700

Data Index: 7738364 (Open Web Text)

Max Activating Token Index: 23

Text #11

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0587. Min Act: -0.1700

Data Index: 3675031 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0336. Min Act: -0.1700

Data Index: 3602432 (Open Web Text)

Max Activating Token Index: 710

Text #13

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0510. Min Act: -0.1700

Data Index: 3382971 (Open Web Text)

Max Activating Token Index: 29

Text #14

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0435. Min Act: -0.1700

Data Index: 5537920 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0401. Min Act: -0.1700

Data Index: 2708598 (Open Web Text)

Max Activating Token Index: 33

Text #16

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0230. Min Act: -0.1700

Data Index: 3777626 (Open Web Text)

Max Activating Token Index: 679

Text #17

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0389. Min Act: -0.1700

Data Index: 3314691 (Open Web Text)

Max Activating Token Index: 410

Text #18

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0243. Min Act: -0.1700

Data Index: 83121 (Open Web Text)

Max Activating Token Index: 67

Text #19

Max Range: 2.1925. Min Range: -2.1925

Max Act: 2.0159. Min Act: -0.1700

Data Index: 2587661 (Open Web Text)

Max Activating Token Index: 820