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

Dataset: Open Web Text

Neuron 785 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: 2.5040. Min Range: -2.5040

Max Act: 2.5040. Min Act: -0.1700

Data Index: 3603315 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4837. Min Act: -0.1700

Data Index: 3813456 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4850. Min Act: -0.1700

Data Index: 6812516 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4634. Min Act: -0.1700

Data Index: 7870943 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4642. Min Act: -0.1699

Data Index: 7452929 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4640. Min Act: -0.1700

Data Index: 5074307 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4513. Min Act: -0.1700

Data Index: 4395051 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4546. Min Act: -0.1700

Data Index: 4120582 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4287. Min Act: -0.1700

Data Index: 3875197 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4305. Min Act: -0.1700

Data Index: 7324237 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4353. Min Act: -0.1700

Data Index: 2166320 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4279. Min Act: -0.1698

Data Index: 2867763 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4346. Min Act: -0.1700

Data Index: 1577133 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4180. Min Act: -0.1700

Data Index: 2280989 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4099. Min Act: -0.1700

Data Index: 7158286 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4134. Min Act: -0.1700

Data Index: 1229707 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.3973. Min Act: -0.1700

Data Index: 6394778 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.3905. Min Act: -0.1700

Data Index: 223639 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.4023. Min Act: -0.1699

Data Index: 3888791 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.5040. Min Range: -2.5040

Max Act: 2.3956. Min Act: -0.1700

Data Index: 6350193 (Open Web Text)

Max Activating Token Index: 9