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

Dataset: Open Web Text

Neuron 1500 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: 3.1798. Min Range: -3.1798

Max Act: 3.1725. Min Act: -0.1700

Data Index: 4677506 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1798. Min Act: -0.1700

Data Index: 574002 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1727. Min Act: -0.1700

Data Index: 5428244 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1435. Min Act: -0.1700

Data Index: 5187217 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1390. Min Act: -0.1700

Data Index: 4005532 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1328. Min Act: -0.1700

Data Index: 1773187 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1269. Min Act: -0.1700

Data Index: 5138012 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1279. Min Act: -0.1700

Data Index: 2496730 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1236. Min Act: -0.1700

Data Index: 5228769 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1225. Min Act: -0.1700

Data Index: 8238031 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1031. Min Act: -0.1700

Data Index: 1371720 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.0993. Min Act: -0.1700

Data Index: 1715058 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1158. Min Act: -0.1700

Data Index: 692977 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1059. Min Act: -0.1700

Data Index: 3266934 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1086. Min Act: -0.1700

Data Index: 7215143 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1197. Min Act: -0.1700

Data Index: 6146548 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1108. Min Act: -0.1700

Data Index: 5596906 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.0854. Min Act: -0.1700

Data Index: 5430065 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1047. Min Act: -0.1700

Data Index: 2325695 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1026. Min Act: -0.1700

Data Index: 5526413 (Open Web Text)

Max Activating Token Index: 6