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

Dataset: Open Web Text

Neuron 1830 in Layer 6

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: 3.6005. Min Range: -3.6005

Max Act: 3.6005. Min Act: -0.1700

Data Index: 2210624 (Open Web Text)

Max Activating Token Index: 935

Text #1

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.4822. Min Act: -0.1700

Data Index: 4095924 (Open Web Text)

Max Activating Token Index: 882

Text #2

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.4476. Min Act: -0.1700

Data Index: 1322138 (Open Web Text)

Max Activating Token Index: 673

Text #3

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.4451. Min Act: -0.1700

Data Index: 3835857 (Open Web Text)

Max Activating Token Index: 870

Text #4

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.4260. Min Act: -0.1700

Data Index: 2514814 (Open Web Text)

Max Activating Token Index: 713

Text #5

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.4259. Min Act: -0.1700

Data Index: 2514800 (Open Web Text)

Max Activating Token Index: 568

Text #6

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.4247. Min Act: -0.1700

Data Index: 4167789 (Open Web Text)

Max Activating Token Index: 653

Text #7

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.4074. Min Act: -0.1700

Data Index: 7910110 (Open Web Text)

Max Activating Token Index: 1006

Text #8

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.3714. Min Act: -0.1700

Data Index: 2173104 (Open Web Text)

Max Activating Token Index: 424

Text #9

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.3322. Min Act: -0.1700

Data Index: 2009791 (Open Web Text)

Max Activating Token Index: 893

Text #10

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.3494. Min Act: -0.1700

Data Index: 4429547 (Open Web Text)

Max Activating Token Index: 985

Text #11

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.3009. Min Act: -0.1700

Data Index: 3370553 (Open Web Text)

Max Activating Token Index: 786

Text #12

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.3387. Min Act: -0.1700

Data Index: 7950875 (Open Web Text)

Max Activating Token Index: 162

Text #13

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.3464. Min Act: -0.1700

Data Index: 2453763 (Open Web Text)

Max Activating Token Index: 351

Text #14

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.3351. Min Act: -0.1700

Data Index: 3728245 (Open Web Text)

Max Activating Token Index: 477

Text #15

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.3634. Min Act: -0.1700

Data Index: 3734479 (Open Web Text)

Max Activating Token Index: 875

Text #16

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.2943. Min Act: -0.1700

Data Index: 4614732 (Open Web Text)

Max Activating Token Index: 995

Text #17

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.3406. Min Act: -0.1700

Data Index: 83601 (Open Web Text)

Max Activating Token Index: 468

Text #18

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.2883. Min Act: -0.1700

Data Index: 7415108 (Open Web Text)

Max Activating Token Index: 928

Text #19

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.3004. Min Act: -0.1700

Data Index: 4295369 (Open Web Text)

Max Activating Token Index: 736