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

Dataset: Open Web Text

Neuron 2809 in Layer 4

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: 2.1943. Min Range: -2.1943

Max Act: 2.1943. Min Act: -0.1700

Data Index: 3649275 (Open Web Text)

Max Activating Token Index: 836

Text #1

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.1666. Min Act: -0.1700

Data Index: 2480384 (Open Web Text)

Max Activating Token Index: 709

Text #2

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.1516. Min Act: -0.1700

Data Index: 6760951 (Open Web Text)

Max Activating Token Index: 972

Text #3

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.1378. Min Act: -0.1700

Data Index: 7640400 (Open Web Text)

Max Activating Token Index: 774

Text #4

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.1283. Min Act: -0.1700

Data Index: 2480386 (Open Web Text)

Max Activating Token Index: 150

Text #5

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.1225. Min Act: -0.1700

Data Index: 5386620 (Open Web Text)

Max Activating Token Index: 772

Text #6

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.1216. Min Act: -0.1700

Data Index: 1985862 (Open Web Text)

Max Activating Token Index: 581

Text #7

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.1075. Min Act: -0.1700

Data Index: 2086102 (Open Web Text)

Max Activating Token Index: 123

Text #8

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.1019. Min Act: -0.1700

Data Index: 5257551 (Open Web Text)

Max Activating Token Index: 977

Text #9

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.1079. Min Act: -0.1700

Data Index: 2398624 (Open Web Text)

Max Activating Token Index: 520

Text #10

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.1152. Min Act: -0.1700

Data Index: 4297441 (Open Web Text)

Max Activating Token Index: 316

Text #11

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.0960. Min Act: -0.1700

Data Index: 1936159 (Open Web Text)

Max Activating Token Index: 253

Text #12

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.0893. Min Act: -0.1700

Data Index: 1030558 (Open Web Text)

Max Activating Token Index: 986

Text #13

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.0776. Min Act: -0.1700

Data Index: 4815831 (Open Web Text)

Max Activating Token Index: 80

Text #14

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.1070. Min Act: -0.1700

Data Index: 4379514 (Open Web Text)

Max Activating Token Index: 151

Text #15

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.0911. Min Act: -0.1700

Data Index: 4692711 (Open Web Text)

Max Activating Token Index: 176

Text #16

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.1062. Min Act: -0.1700

Data Index: 5611889 (Open Web Text)

Max Activating Token Index: 991

Text #17

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.0866. Min Act: -0.1700

Data Index: 4750935 (Open Web Text)

Max Activating Token Index: 37

Text #18

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.0814. Min Act: -0.1700

Data Index: 7987672 (Open Web Text)

Max Activating Token Index: 665

Text #19

Max Range: 2.1943. Min Range: -2.1943

Max Act: 2.0847. Min Act: -0.1700

Data Index: 3181564 (Open Web Text)

Max Activating Token Index: 201