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

Dataset: Open Web Text

Neuron 912 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: 3.4102. Min Range: -3.4102

Max Act: 3.4102. Min Act: -0.1700

Data Index: 7282189 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.3174. Min Act: -0.1700

Data Index: 5452185 (Open Web Text)

Max Activating Token Index: 560

Text #2

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2955. Min Act: -0.1700

Data Index: 5528384 (Open Web Text)

Max Activating Token Index: 96

Text #3

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.3122. Min Act: -0.1700

Data Index: 4759261 (Open Web Text)

Max Activating Token Index: 98

Text #4

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2924. Min Act: -0.1700

Data Index: 2758322 (Open Web Text)

Max Activating Token Index: 54

Text #5

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2969. Min Act: -0.1700

Data Index: 7439182 (Open Web Text)

Max Activating Token Index: 326

Text #6

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2822. Min Act: -0.1700

Data Index: 3871741 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2760. Min Act: -0.1700

Data Index: 591378 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2732. Min Act: -0.1700

Data Index: 3714390 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2752. Min Act: -0.1700

Data Index: 642768 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2883. Min Act: -0.1700

Data Index: 5162326 (Open Web Text)

Max Activating Token Index: 91

Text #11

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2760. Min Act: -0.1700

Data Index: 7909313 (Open Web Text)

Max Activating Token Index: 95

Text #12

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2797. Min Act: -0.1700

Data Index: 333108 (Open Web Text)

Max Activating Token Index: 377

Text #13

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2546. Min Act: -0.1700

Data Index: 5403751 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2559. Min Act: -0.1700

Data Index: 1731026 (Open Web Text)

Max Activating Token Index: 589

Text #15

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2809. Min Act: -0.1700

Data Index: 3200406 (Open Web Text)

Max Activating Token Index: 498

Text #16

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2692. Min Act: -0.1700

Data Index: 7458742 (Open Web Text)

Max Activating Token Index: 783

Text #17

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2590. Min Act: -0.1700

Data Index: 5061396 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2650. Min Act: -0.1700

Data Index: 7247485 (Open Web Text)

Max Activating Token Index: 135

Text #19

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2426. Min Act: -0.1700

Data Index: 5153897 (Open Web Text)

Max Activating Token Index: 12