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

Dataset: Open Web Text

Neuron 199 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: 6.3123. Min Range: -6.3123

Max Act: 6.3123. Min Act: -0.1700

Data Index: 921753 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.2972. Min Act: -0.1700

Data Index: 7244318 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.2544. Min Act: -0.1700

Data Index: 3973046 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.2098. Min Act: -0.1700

Data Index: 1022444 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.2147. Min Act: -0.1700

Data Index: 2140142 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.2147. Min Act: -0.1700

Data Index: 5401280 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.2206. Min Act: -0.1700

Data Index: 7856886 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.2063. Min Act: -0.1700

Data Index: 1268674 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.2060. Min Act: -0.1700

Data Index: 3044561 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.2147. Min Act: -0.1700

Data Index: 3680282 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.2147. Min Act: -0.1700

Data Index: 2585463 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.2155. Min Act: -0.1700

Data Index: 5999274 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.1838. Min Act: -0.1700

Data Index: 6941146 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.1948. Min Act: -0.1700

Data Index: 6405032 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.1695. Min Act: -0.1700

Data Index: 4237505 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.2033. Min Act: -0.1700

Data Index: 6123200 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.1757. Min Act: -0.1700

Data Index: 5508980 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.1749. Min Act: -0.1700

Data Index: 118847 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.1927. Min Act: -0.1700

Data Index: 1801975 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 6.3123. Min Range: -6.3123

Max Act: 6.1852. Min Act: -0.1700

Data Index: 5469340 (Open Web Text)

Max Activating Token Index: 3