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

Dataset: Open Web Text

Neuron 1088 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: 2.2522. Min Range: -2.2522

Max Act: 2.2522. Min Act: -0.1700

Data Index: 6148299 (Open Web Text)

Max Activating Token Index: 63

Text #1

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.2383. Min Act: -0.1700

Data Index: 2912663 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1742. Min Act: -0.1700

Data Index: 8264954 (Open Web Text)

Max Activating Token Index: 397

Text #3

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1816. Min Act: -0.1700

Data Index: 2231361 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1848. Min Act: -0.1697

Data Index: 6170780 (Open Web Text)

Max Activating Token Index: 612

Text #5

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1735. Min Act: -0.1700

Data Index: 3456274 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1708. Min Act: -0.1700

Data Index: 4735580 (Open Web Text)

Max Activating Token Index: 291

Text #7

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1555. Min Act: -0.1700

Data Index: 5490498 (Open Web Text)

Max Activating Token Index: 179

Text #8

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1148. Min Act: -0.1700

Data Index: 190883 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1173. Min Act: -0.1700

Data Index: 413793 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1284. Min Act: -0.1700

Data Index: 6369945 (Open Web Text)

Max Activating Token Index: 151

Text #11

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1080. Min Act: -0.1700

Data Index: 5183431 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1046. Min Act: -0.1700

Data Index: 5254774 (Open Web Text)

Max Activating Token Index: 1000

Text #13

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1023. Min Act: -0.1700

Data Index: 5088784 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.0988. Min Act: -0.1700

Data Index: 6638544 (Open Web Text)

Max Activating Token Index: 954

Text #15

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.0964. Min Act: -0.1700

Data Index: 3311395 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.0951. Min Act: -0.1700

Data Index: 1398600 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1215. Min Act: -0.1700

Data Index: 1199490 (Open Web Text)

Max Activating Token Index: 478

Text #18

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.0959. Min Act: -0.1700

Data Index: 1043311 (Open Web Text)

Max Activating Token Index: 520

Text #19

Max Range: 2.2522. Min Range: -2.2522

Max Act: 2.1047. Min Act: -0.1700

Data Index: 2081830 (Open Web Text)

Max Activating Token Index: 24