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

Dataset: Open Web Text

Neuron 1275 in Layer 2

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: 4.2085. Min Range: -4.2085

Max Act: 4.2085. Min Act: -0.1700

Data Index: 6624658 (Open Web Text)

Max Activating Token Index: 981

Text #1

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0945. Min Act: -0.1700

Data Index: 2448978 (Open Web Text)

Max Activating Token Index: 157

Text #2

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0845. Min Act: -0.1700

Data Index: 2341326 (Open Web Text)

Max Activating Token Index: 366

Text #3

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.1253. Min Act: -0.1700

Data Index: 1897775 (Open Web Text)

Max Activating Token Index: 991

Text #4

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0997. Min Act: -0.1700

Data Index: 3159451 (Open Web Text)

Max Activating Token Index: 846

Text #5

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0580. Min Act: -0.1700

Data Index: 8441573 (Open Web Text)

Max Activating Token Index: 580

Text #6

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0836. Min Act: -0.1700

Data Index: 6227973 (Open Web Text)

Max Activating Token Index: 615

Text #7

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0706. Min Act: -0.1700

Data Index: 5550202 (Open Web Text)

Max Activating Token Index: 905

Text #8

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0524. Min Act: -0.1700

Data Index: 8817882 (Open Web Text)

Max Activating Token Index: 885

Text #9

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0737. Min Act: -0.1700

Data Index: 4549416 (Open Web Text)

Max Activating Token Index: 227

Text #10

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0868. Min Act: -0.1700

Data Index: 7709595 (Open Web Text)

Max Activating Token Index: 1018

Text #11

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0508. Min Act: -0.1700

Data Index: 7092411 (Open Web Text)

Max Activating Token Index: 1007

Text #12

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0686. Min Act: -0.1700

Data Index: 4703607 (Open Web Text)

Max Activating Token Index: 1003

Text #13

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0333. Min Act: -0.1700

Data Index: 3665372 (Open Web Text)

Max Activating Token Index: 551

Text #14

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0477. Min Act: -0.1700

Data Index: 8548565 (Open Web Text)

Max Activating Token Index: 813

Text #15

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0550. Min Act: -0.1700

Data Index: 2563360 (Open Web Text)

Max Activating Token Index: 898

Text #16

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0427. Min Act: -0.1700

Data Index: 4886920 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0481. Min Act: -0.1700

Data Index: 7674161 (Open Web Text)

Max Activating Token Index: 517

Text #18

Max Range: 4.2085. Min Range: -4.2085

Max Act: 4.0276. Min Act: -0.1700

Data Index: 645717 (Open Web Text)

Max Activating Token Index: 472

Text #19

Max Range: 4.2085. Min Range: -4.2085

Max Act: 3.9999. Min Act: -0.1700

Data Index: 5136640 (Open Web Text)

Max Activating Token Index: 992