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

Dataset: Open Web Text

Neuron 991 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: 6.1194. Min Range: -6.1194

Max Act: 6.1194. Min Act: -0.1700

Data Index: 6065291 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 6.1194. Min Range: -6.1194

Max Act: 6.1130. Min Act: -0.1700

Data Index: 1637956 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 6.1194. Min Range: -6.1194

Max Act: 6.0778. Min Act: -0.1700

Data Index: 7169866 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 6.1194. Min Range: -6.1194

Max Act: 6.0124. Min Act: -0.1700

Data Index: 4321525 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9966. Min Act: -0.1700

Data Index: 660472 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9582. Min Act: -0.1700

Data Index: 3877023 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9744. Min Act: -0.1700

Data Index: 7362996 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9666. Min Act: -0.1700

Data Index: 6358314 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9880. Min Act: -0.1700

Data Index: 194273 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9419. Min Act: -0.1700

Data Index: 1663037 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9205. Min Act: -0.1700

Data Index: 6049874 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9404. Min Act: -0.1700

Data Index: 6629351 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9354. Min Act: -0.1700

Data Index: 5955992 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.8990. Min Act: -0.1700

Data Index: 3246068 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9250. Min Act: -0.1700

Data Index: 6157259 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9079. Min Act: -0.1700

Data Index: 6540308 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.8961. Min Act: -0.1700

Data Index: 1156852 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9291. Min Act: -0.1700

Data Index: 8609888 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9007. Min Act: -0.1700

Data Index: 2044279 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 6.1194. Min Range: -6.1194

Max Act: 5.9043. Min Act: -0.1700

Data Index: 4626539 (Open Web Text)

Max Activating Token Index: 4