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

Dataset: Open Web Text

Neuron 1746 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: 6.0188. Min Range: -6.0188

Max Act: 6.0188. Min Act: -0.1700

Data Index: 4835818 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.9608. Min Act: -0.1700

Data Index: 3028790 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.9001. Min Act: -0.1700

Data Index: 6659956 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.8180. Min Act: -0.1700

Data Index: 8742693 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.8150. Min Act: -0.1700

Data Index: 3726139 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.8044. Min Act: -0.1700

Data Index: 7922750 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.7528. Min Act: -0.1700

Data Index: 4101584 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.7497. Min Act: -0.1700

Data Index: 7924835 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.7503. Min Act: -0.1700

Data Index: 4807715 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.7438. Min Act: -0.1700

Data Index: 5886364 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.7458. Min Act: -0.1700

Data Index: 7076705 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.7348. Min Act: -0.1700

Data Index: 3012698 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.7168. Min Act: -0.1698

Data Index: 5521473 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.6819. Min Act: -0.1700

Data Index: 6917322 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.6838. Min Act: -0.1700

Data Index: 2757319 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.6990. Min Act: -0.1700

Data Index: 6846927 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.6940. Min Act: -0.1700

Data Index: 4402669 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.6575. Min Act: -0.1700

Data Index: 7529138 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.6526. Min Act: -0.1700

Data Index: 7191838 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 6.0188. Min Range: -6.0188

Max Act: 5.6525. Min Act: -0.1700

Data Index: 5051264 (Open Web Text)

Max Activating Token Index: 4