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

Dataset: Open Web Text

Neuron 3039 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: 4.0360. Min Range: -4.0360

Max Act: 4.0360. Min Act: -0.1700

Data Index: 899107 (Open Web Text)

Max Activating Token Index: 929

Text #1

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9668. Min Act: -0.1700

Data Index: 5519625 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9705. Min Act: -0.1700

Data Index: 8222337 (Open Web Text)

Max Activating Token Index: 878

Text #3

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9753. Min Act: -0.1700

Data Index: 307160 (Open Web Text)

Max Activating Token Index: 934

Text #4

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9854. Min Act: -0.1700

Data Index: 2330570 (Open Web Text)

Max Activating Token Index: 807

Text #5

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9362. Min Act: -0.1700

Data Index: 3392646 (Open Web Text)

Max Activating Token Index: 868

Text #6

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9136. Min Act: -0.1700

Data Index: 5047392 (Open Web Text)

Max Activating Token Index: 998

Text #7

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9509. Min Act: -0.1700

Data Index: 2609865 (Open Web Text)

Max Activating Token Index: 931

Text #8

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9332. Min Act: -0.1700

Data Index: 4675821 (Open Web Text)

Max Activating Token Index: 680

Text #9

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9254. Min Act: -0.1700

Data Index: 3603527 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9030. Min Act: -0.1700

Data Index: 8486891 (Open Web Text)

Max Activating Token Index: 977

Text #11

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9070. Min Act: -0.1700

Data Index: 5331570 (Open Web Text)

Max Activating Token Index: 802

Text #12

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9086. Min Act: -0.1700

Data Index: 5318720 (Open Web Text)

Max Activating Token Index: 806

Text #13

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9154. Min Act: -0.1700

Data Index: 3780921 (Open Web Text)

Max Activating Token Index: 893

Text #14

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9230. Min Act: -0.1700

Data Index: 5360513 (Open Web Text)

Max Activating Token Index: 845

Text #15

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.8896. Min Act: -0.1700

Data Index: 7286439 (Open Web Text)

Max Activating Token Index: 66

Text #16

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9129. Min Act: -0.1700

Data Index: 936002 (Open Web Text)

Max Activating Token Index: 675

Text #17

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9098. Min Act: -0.1700

Data Index: 2135567 (Open Web Text)

Max Activating Token Index: 881

Text #18

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.8982. Min Act: -0.1700

Data Index: 7185960 (Open Web Text)

Max Activating Token Index: 906

Text #19

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.8829. Min Act: -0.1700

Data Index: 1248017 (Open Web Text)

Max Activating Token Index: 882