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

Dataset: Open Web Text

Neuron 2264 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: 2.7188. Min Range: -2.7188

Max Act: 2.7188. Min Act: -0.1700

Data Index: 6185892 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6895. Min Act: -0.1700

Data Index: 3701674 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.7004. Min Act: -0.1700

Data Index: 7035995 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6906. Min Act: -0.1700

Data Index: 1254717 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6620. Min Act: -0.1700

Data Index: 5585453 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6723. Min Act: -0.1700

Data Index: 7172239 (Open Web Text)

Max Activating Token Index: 34

Text #6

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6562. Min Act: -0.1700

Data Index: 3212963 (Open Web Text)

Max Activating Token Index: 123

Text #7

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6382. Min Act: -0.1700

Data Index: 1856234 (Open Web Text)

Max Activating Token Index: 73

Text #8

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6388. Min Act: -0.1700

Data Index: 8581139 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6417. Min Act: -0.1700

Data Index: 4575398 (Open Web Text)

Max Activating Token Index: 352

Text #10

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6312. Min Act: -0.1700

Data Index: 8544257 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6148. Min Act: -0.1700

Data Index: 7706344 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6256. Min Act: -0.1700

Data Index: 8737712 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6299. Min Act: -0.1700

Data Index: 2068147 (Open Web Text)

Max Activating Token Index: 162

Text #14

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6176. Min Act: -0.1700

Data Index: 4495265 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6157. Min Act: -0.1700

Data Index: 4219188 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6039. Min Act: -0.1700

Data Index: 4653284 (Open Web Text)

Max Activating Token Index: 416

Text #17

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.6111. Min Act: -0.1700

Data Index: 6558060 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.5813. Min Act: -0.1700

Data Index: 3248631 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 2.7188. Min Range: -2.7188

Max Act: 2.5925. Min Act: -0.1700

Data Index: 3027094 (Open Web Text)

Max Activating Token Index: 3