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

Dataset: Open Web Text

Neuron 1160 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: 3.9054. Min Range: -3.9054

Max Act: 3.8888. Min Act: -0.1700

Data Index: 7286443 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.9054. Min Act: -0.1700

Data Index: 7798561 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8847. Min Act: -0.1700

Data Index: 4311275 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8629. Min Act: -0.1700

Data Index: 6654220 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8878. Min Act: -0.1700

Data Index: 1292788 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8745. Min Act: -0.1700

Data Index: 7798252 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8832. Min Act: -0.1700

Data Index: 3193363 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8600. Min Act: -0.1700

Data Index: 1515447 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8674. Min Act: -0.1700

Data Index: 3776981 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8740. Min Act: -0.1700

Data Index: 8094228 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8834. Min Act: -0.1700

Data Index: 5488261 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8656. Min Act: -0.1700

Data Index: 251176 (Open Web Text)

Max Activating Token Index: 34

Text #12

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8865. Min Act: -0.1700

Data Index: 689999 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8266. Min Act: -0.1700

Data Index: 4538068 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8522. Min Act: -0.1700

Data Index: 2234565 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8437. Min Act: -0.1700

Data Index: 4180422 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8316. Min Act: -0.1700

Data Index: 3824173 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8243. Min Act: -0.1700

Data Index: 2179113 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8270. Min Act: -0.1700

Data Index: 2063075 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8270. Min Act: -0.1700

Data Index: 214908 (Open Web Text)

Max Activating Token Index: 42