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

Dataset: Open Web Text

Neuron 1086 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: 0.4877. Min Range: -0.4877

Max Act: 0.4877. Min Act: -0.1145

Data Index: 3368016 (Open Web Text)

Max Activating Token Index: 980

Text #1

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4854. Min Act: -0.1047

Data Index: 1432862 (Open Web Text)

Max Activating Token Index: 965

Text #2

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4742. Min Act: -0.1188

Data Index: 1339823 (Open Web Text)

Max Activating Token Index: 965

Text #3

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4609. Min Act: -0.0985

Data Index: 4959674 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4619. Min Act: -0.0995

Data Index: 5958808 (Open Web Text)

Max Activating Token Index: 933

Text #5

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4669. Min Act: -0.1088

Data Index: 8596922 (Open Web Text)

Max Activating Token Index: 986

Text #6

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4663. Min Act: -0.1138

Data Index: 8608891 (Open Web Text)

Max Activating Token Index: 956

Text #7

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4565. Min Act: -0.1240

Data Index: 21 (Open Web Text)

Max Activating Token Index: 0

Text #8

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4565. Min Act: -0.1084

Data Index: 20 (Open Web Text)

Max Activating Token Index: 0

Text #9

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4565. Min Act: -0.1014

Data Index: 22 (Open Web Text)

Max Activating Token Index: 0

Text #10

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4565. Min Act: -0.1182

Data Index: 23 (Open Web Text)

Max Activating Token Index: 0

Text #11

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4565. Min Act: -0.0921

Data Index: 11 (Open Web Text)

Max Activating Token Index: 0

Text #12

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4565. Min Act: -0.1047

Data Index: 10 (Open Web Text)

Max Activating Token Index: 0

Text #13

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4565. Min Act: -0.1074

Data Index: 8 (Open Web Text)

Max Activating Token Index: 0

Text #14

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4565. Min Act: -0.1106

Data Index: 9 (Open Web Text)

Max Activating Token Index: 0

Text #15

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4565. Min Act: -0.1281

Data Index: 13 (Open Web Text)

Max Activating Token Index: 0

Text #16

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4565. Min Act: -0.1132

Data Index: 12 (Open Web Text)

Max Activating Token Index: 0

Text #17

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4565. Min Act: -0.0991

Data Index: 14 (Open Web Text)

Max Activating Token Index: 0

Text #18

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4565. Min Act: -0.1024

Data Index: 15 (Open Web Text)

Max Activating Token Index: 0

Text #19

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4565. Min Act: -0.1083

Data Index: 3 (Open Web Text)

Max Activating Token Index: 0