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

Dataset: Open Web Text

Neuron 1472 in Layer 1

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: 1.9616. Min Range: -1.9616

Max Act: 1.9575. Min Act: -0.1700

Data Index: 6086526 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9526. Min Act: -0.1700

Data Index: 4126829 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9433. Min Act: -0.1700

Data Index: 3588648 (Open Web Text)

Max Activating Token Index: 695

Text #3

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9616. Min Act: -0.1700

Data Index: 2922217 (Open Web Text)

Max Activating Token Index: 658

Text #4

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9416. Min Act: -0.1700

Data Index: 6496371 (Open Web Text)

Max Activating Token Index: 677

Text #5

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9207. Min Act: -0.1700

Data Index: 4430978 (Open Web Text)

Max Activating Token Index: 45

Text #6

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9297. Min Act: -0.1700

Data Index: 8285941 (Open Web Text)

Max Activating Token Index: 227

Text #7

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9161. Min Act: -0.1700

Data Index: 8264320 (Open Web Text)

Max Activating Token Index: 26

Text #8

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9195. Min Act: -0.1700

Data Index: 6290876 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9234. Min Act: -0.1700

Data Index: 2884907 (Open Web Text)

Max Activating Token Index: 677

Text #10

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9254. Min Act: -0.1700

Data Index: 2087644 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9076. Min Act: -0.1700

Data Index: 2761185 (Open Web Text)

Max Activating Token Index: 639

Text #12

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9060. Min Act: -0.1700

Data Index: 5899100 (Open Web Text)

Max Activating Token Index: 230

Text #13

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.8937. Min Act: -0.1700

Data Index: 5640039 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9191. Min Act: -0.1700

Data Index: 386573 (Open Web Text)

Max Activating Token Index: 406

Text #15

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9167. Min Act: -0.1700

Data Index: 5429447 (Open Web Text)

Max Activating Token Index: 121

Text #16

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9094. Min Act: -0.1700

Data Index: 4815827 (Open Web Text)

Max Activating Token Index: 554

Text #17

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.8809. Min Act: -0.1700

Data Index: 315610 (Open Web Text)

Max Activating Token Index: 663

Text #18

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9089. Min Act: -0.1700

Data Index: 1867736 (Open Web Text)

Max Activating Token Index: 793

Text #19

Max Range: 1.9616. Min Range: -1.9616

Max Act: 1.9028. Min Act: -0.1700

Data Index: 4440294 (Open Web Text)

Max Activating Token Index: 776