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

Dataset: Open Web Text

Neuron 357 in Layer 0

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: 5.3992. Min Range: -5.3992

Max Act: 5.3992. Min Act: -0.1700

Data Index: 600603 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.3928. Min Act: -0.1700

Data Index: 6700703 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.3136. Min Act: -0.1700

Data Index: 1423717 (Open Web Text)

Max Activating Token Index: 15

Text #3

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.3163. Min Act: -0.1700

Data Index: 3241101 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.3258. Min Act: -0.1700

Data Index: 7226228 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.3290. Min Act: -0.1698

Data Index: 6750847 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2981. Min Act: -0.1700

Data Index: 4376265 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.3004. Min Act: -0.1700

Data Index: 5115134 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2854. Min Act: -0.1700

Data Index: 7231637 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2952. Min Act: -0.1699

Data Index: 5638874 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2998. Min Act: -0.1700

Data Index: 2435535 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2534. Min Act: -0.1699

Data Index: 8299047 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2459. Min Act: -0.1700

Data Index: 126734 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2640. Min Act: -0.1698

Data Index: 4321182 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2584. Min Act: -0.1700

Data Index: 6446796 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2569. Min Act: -0.1699

Data Index: 5606324 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2573. Min Act: -0.1700

Data Index: 5345708 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2710. Min Act: -0.1700

Data Index: 5292190 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2697. Min Act: -0.1700

Data Index: 4970609 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2478. Min Act: -0.1700

Data Index: 4377226 (Open Web Text)

Max Activating Token Index: 11