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

Dataset: Open Web Text

Neuron 2307 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: 4.5693. Min Range: -4.5693

Max Act: 4.5693. Min Act: -0.1700

Data Index: 3788605 (Open Web Text)

Max Activating Token Index: 514

Text #1

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.4526. Min Act: -0.1700

Data Index: 5644085 (Open Web Text)

Max Activating Token Index: 375

Text #2

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.4690. Min Act: -0.1700

Data Index: 6347086 (Open Web Text)

Max Activating Token Index: 743

Text #3

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3889. Min Act: -0.1700

Data Index: 8487834 (Open Web Text)

Max Activating Token Index: 761

Text #4

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3663. Min Act: -0.1700

Data Index: 3907182 (Open Web Text)

Max Activating Token Index: 846

Text #5

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3774. Min Act: -0.1700

Data Index: 8149931 (Open Web Text)

Max Activating Token Index: 954

Text #6

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3679. Min Act: -0.1700

Data Index: 7720745 (Open Web Text)

Max Activating Token Index: 486

Text #7

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3905. Min Act: -0.1700

Data Index: 233563 (Open Web Text)

Max Activating Token Index: 695

Text #8

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3861. Min Act: -0.1700

Data Index: 3107927 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3049. Min Act: -0.1700

Data Index: 7544542 (Open Web Text)

Max Activating Token Index: 523

Text #10

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3462. Min Act: -0.1700

Data Index: 4685618 (Open Web Text)

Max Activating Token Index: 534

Text #11

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.2970. Min Act: -0.1700

Data Index: 7075922 (Open Web Text)

Max Activating Token Index: 594

Text #12

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3401. Min Act: -0.1700

Data Index: 6709672 (Open Web Text)

Max Activating Token Index: 237

Text #13

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3556. Min Act: -0.1700

Data Index: 6595616 (Open Web Text)

Max Activating Token Index: 400

Text #14

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3616. Min Act: -0.1700

Data Index: 3398909 (Open Web Text)

Max Activating Token Index: 298

Text #15

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3367. Min Act: -0.1700

Data Index: 5882039 (Open Web Text)

Max Activating Token Index: 424

Text #16

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3220. Min Act: -0.1700

Data Index: 5859092 (Open Web Text)

Max Activating Token Index: 178

Text #17

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3171. Min Act: -0.1700

Data Index: 81232 (Open Web Text)

Max Activating Token Index: 765

Text #18

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3217. Min Act: -0.1700

Data Index: 909849 (Open Web Text)

Max Activating Token Index: 890

Text #19

Max Range: 4.5693. Min Range: -4.5693

Max Act: 4.3250. Min Act: -0.1700

Data Index: 2298405 (Open Web Text)

Max Activating Token Index: 260