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

Dataset: Open Web Text

Neuron 1524 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: 1.0421. Min Range: -1.0421

Max Act: 1.0421. Min Act: -0.1700

Data Index: 2954235 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.0421. Min Range: -1.0421

Max Act: 1.0323. Min Act: -0.1700

Data Index: 1147895 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 1.0421. Min Range: -1.0421

Max Act: 1.0207. Min Act: -0.1700

Data Index: 7195560 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.0421. Min Range: -1.0421

Max Act: 1.0307. Min Act: -0.1700

Data Index: 6315319 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 1.0421. Min Range: -1.0421

Max Act: 1.0174. Min Act: -0.1700

Data Index: 6848259 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.0421. Min Range: -1.0421

Max Act: 1.0178. Min Act: -0.1700

Data Index: 7923941 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 1.0421. Min Range: -1.0421

Max Act: 1.0193. Min Act: -0.1700

Data Index: 3649689 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 1.0421. Min Range: -1.0421

Max Act: 1.0178. Min Act: -0.1700

Data Index: 4410900 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 1.0421. Min Range: -1.0421

Max Act: 1.0112. Min Act: -0.1700

Data Index: 614830 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9986. Min Act: -0.1700

Data Index: 7827221 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9927. Min Act: -0.1700

Data Index: 2231607 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 1.0421. Min Range: -1.0421

Max Act: 1.0002. Min Act: -0.1700

Data Index: 7132572 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 1.0421. Min Range: -1.0421

Max Act: 1.0075. Min Act: -0.1700

Data Index: 4056193 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9984. Min Act: -0.1700

Data Index: 7140220 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9908. Min Act: -0.1700

Data Index: 396803 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9909. Min Act: -0.1700

Data Index: 7014685 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9958. Min Act: -0.1700

Data Index: 3632697 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9965. Min Act: -0.1700

Data Index: 1282312 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9929. Min Act: -0.1700

Data Index: 3020816 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9876. Min Act: -0.1700

Data Index: 11308 (Open Web Text)

Max Activating Token Index: 3