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

Dataset: Open Web Text

Neuron 2335 in Layer 2

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: 1.0257. Min Range: -1.0257

Max Act: 1.0257. Min Act: -0.1700

Data Index: 4583421 (Open Web Text)

Max Activating Token Index: 97

Text #1

Max Range: 1.0257. Min Range: -1.0257

Max Act: 1.0087. Min Act: -0.1700

Data Index: 2083827 (Open Web Text)

Max Activating Token Index: 60

Text #2

Max Range: 1.0257. Min Range: -1.0257

Max Act: 1.0087. Min Act: -0.1700

Data Index: 4469546 (Open Web Text)

Max Activating Token Index: 97

Text #3

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9926. Min Act: -0.1700

Data Index: 64006 (Open Web Text)

Max Activating Token Index: 60

Text #4

Max Range: 1.0257. Min Range: -1.0257

Max Act: 1.0154. Min Act: -0.1700

Data Index: 4679115 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9898. Min Act: -0.1700

Data Index: 6283944 (Open Web Text)

Max Activating Token Index: 99

Text #6

Max Range: 1.0257. Min Range: -1.0257

Max Act: 1.0058. Min Act: -0.1700

Data Index: 160801 (Open Web Text)

Max Activating Token Index: 102

Text #7

Max Range: 1.0257. Min Range: -1.0257

Max Act: 1.0020. Min Act: -0.1700

Data Index: 5735967 (Open Web Text)

Max Activating Token Index: 115

Text #8

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9870. Min Act: -0.1700

Data Index: 4118697 (Open Web Text)

Max Activating Token Index: 102

Text #9

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9986. Min Act: -0.1700

Data Index: 4446942 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9996. Min Act: -0.1700

Data Index: 5287291 (Open Web Text)

Max Activating Token Index: 111

Text #11

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9714. Min Act: -0.1700

Data Index: 3528229 (Open Web Text)

Max Activating Token Index: 68

Text #12

Max Range: 1.0257. Min Range: -1.0257

Max Act: 1.0068. Min Act: -0.1700

Data Index: 4768368 (Open Web Text)

Max Activating Token Index: 83

Text #13

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9828. Min Act: -0.1700

Data Index: 1202335 (Open Web Text)

Max Activating Token Index: 105

Text #14

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9756. Min Act: -0.1700

Data Index: 131748 (Open Web Text)

Max Activating Token Index: 70

Text #15

Max Range: 1.0257. Min Range: -1.0257

Max Act: 1.0011. Min Act: -0.1700

Data Index: 1567957 (Open Web Text)

Max Activating Token Index: 75

Text #16

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9745. Min Act: -0.1700

Data Index: 7636015 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9868. Min Act: -0.1700

Data Index: 4169352 (Open Web Text)

Max Activating Token Index: 77

Text #18

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9906. Min Act: -0.1700

Data Index: 6009277 (Open Web Text)

Max Activating Token Index: 79

Text #19

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9862. Min Act: -0.1700

Data Index: 6196463 (Open Web Text)

Max Activating Token Index: 54