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

Dataset: Open Web Text

Neuron 40 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: 3.2046. Min Range: -3.2046

Max Act: 3.2046. Min Act: -0.1700

Data Index: 1777309 (Open Web Text)

Max Activating Token Index: 875

Text #1

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.1942. Min Act: -0.1700

Data Index: 6977628 (Open Web Text)

Max Activating Token Index: 832

Text #2

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.1705. Min Act: -0.1700

Data Index: 1259788 (Open Web Text)

Max Activating Token Index: 650

Text #3

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.1715. Min Act: -0.1700

Data Index: 7715781 (Open Web Text)

Max Activating Token Index: 179

Text #4

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.1387. Min Act: -0.1700

Data Index: 3462943 (Open Web Text)

Max Activating Token Index: 631

Text #5

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.1794. Min Act: -0.1700

Data Index: 4096154 (Open Web Text)

Max Activating Token Index: 994

Text #6

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.1431. Min Act: -0.1700

Data Index: 4013908 (Open Web Text)

Max Activating Token Index: 412

Text #7

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.1457. Min Act: -0.1700

Data Index: 220338 (Open Web Text)

Max Activating Token Index: 744

Text #8

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.0930. Min Act: -0.1700

Data Index: 7163492 (Open Web Text)

Max Activating Token Index: 875

Text #9

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.1103. Min Act: -0.1700

Data Index: 7871409 (Open Web Text)

Max Activating Token Index: 423

Text #10

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.1169. Min Act: -0.1700

Data Index: 4836645 (Open Web Text)

Max Activating Token Index: 199

Text #11

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.1134. Min Act: -0.1700

Data Index: 5271833 (Open Web Text)

Max Activating Token Index: 470

Text #12

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.1438. Min Act: -0.1700

Data Index: 8173490 (Open Web Text)

Max Activating Token Index: 648

Text #13

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.1117. Min Act: -0.1700

Data Index: 5027664 (Open Web Text)

Max Activating Token Index: 366

Text #14

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.0826. Min Act: -0.1700

Data Index: 4254013 (Open Web Text)

Max Activating Token Index: 86

Text #15

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.0664. Min Act: -0.1700

Data Index: 6674022 (Open Web Text)

Max Activating Token Index: 50

Text #16

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.1039. Min Act: -0.1700

Data Index: 6590723 (Open Web Text)

Max Activating Token Index: 631

Text #17

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.0929. Min Act: -0.1700

Data Index: 4118045 (Open Web Text)

Max Activating Token Index: 922

Text #18

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.0836. Min Act: -0.1700

Data Index: 6365781 (Open Web Text)

Max Activating Token Index: 654

Text #19

Max Range: 3.2046. Min Range: -3.2046

Max Act: 3.0573. Min Act: -0.1700

Data Index: 35640 (Open Web Text)

Max Activating Token Index: 232