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

Dataset: Open Web Text

Neuron 2444 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: 2.5900. Min Range: -2.5900

Max Act: 2.5900. Min Act: -0.1700

Data Index: 2161993 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.5687. Min Act: -0.1700

Data Index: 6396198 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.5584. Min Act: -0.1700

Data Index: 8807022 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.5231. Min Act: -0.1700

Data Index: 6592189 (Open Web Text)

Max Activating Token Index: 258

Text #4

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.5260. Min Act: -0.1700

Data Index: 3821525 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.5172. Min Act: -0.1700

Data Index: 3670413 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.5089. Min Act: -0.1700

Data Index: 7476241 (Open Web Text)

Max Activating Token Index: 540

Text #7

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.5112. Min Act: -0.1700

Data Index: 3393333 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.5111. Min Act: -0.1700

Data Index: 5525369 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.5154. Min Act: -0.1700

Data Index: 4997113 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.5052. Min Act: -0.1700

Data Index: 8230542 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.5052. Min Act: -0.1700

Data Index: 4672888 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.4985. Min Act: -0.1700

Data Index: 6452821 (Open Web Text)

Max Activating Token Index: 576

Text #13

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.4846. Min Act: -0.1700

Data Index: 2716474 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.4898. Min Act: -0.1700

Data Index: 1606760 (Open Web Text)

Max Activating Token Index: 27

Text #15

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.4860. Min Act: -0.1700

Data Index: 4379010 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.4769. Min Act: -0.1700

Data Index: 8230543 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.4585. Min Act: -0.1700

Data Index: 313938 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.4683. Min Act: -0.1700

Data Index: 6847548 (Open Web Text)

Max Activating Token Index: 534

Text #19

Max Range: 2.5900. Min Range: -2.5900

Max Act: 2.4670. Min Act: -0.1700

Data Index: 8230540 (Open Web Text)

Max Activating Token Index: 3