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

Dataset: Open Web Text

Neuron 43 in Layer 4

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: 4.3853. Min Range: -4.3853

Max Act: 4.3853. Min Act: -0.1700

Data Index: 7035779 (Open Web Text)

Max Activating Token Index: 219

Text #1

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.3836. Min Act: -0.1700

Data Index: 4182786 (Open Web Text)

Max Activating Token Index: 376

Text #2

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.3337. Min Act: -0.1700

Data Index: 1645745 (Open Web Text)

Max Activating Token Index: 776

Text #3

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.3794. Min Act: -0.1700

Data Index: 6126903 (Open Web Text)

Max Activating Token Index: 481

Text #4

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.3103. Min Act: -0.1700

Data Index: 5746400 (Open Web Text)

Max Activating Token Index: 570

Text #5

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.3257. Min Act: -0.1700

Data Index: 6699257 (Open Web Text)

Max Activating Token Index: 454

Text #6

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.2815. Min Act: -0.1700

Data Index: 3593492 (Open Web Text)

Max Activating Token Index: 503

Text #7

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.3029. Min Act: -0.1700

Data Index: 1143156 (Open Web Text)

Max Activating Token Index: 442

Text #8

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.2778. Min Act: -0.1700

Data Index: 4033511 (Open Web Text)

Max Activating Token Index: 481

Text #9

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.2648. Min Act: -0.1700

Data Index: 3420718 (Open Web Text)

Max Activating Token Index: 871

Text #10

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.2473. Min Act: -0.1700

Data Index: 5741113 (Open Web Text)

Max Activating Token Index: 823

Text #11

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.2694. Min Act: -0.1700

Data Index: 2175613 (Open Web Text)

Max Activating Token Index: 781

Text #12

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.2578. Min Act: -0.1700

Data Index: 6793195 (Open Web Text)

Max Activating Token Index: 821

Text #13

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.2429. Min Act: -0.1700

Data Index: 6543095 (Open Web Text)

Max Activating Token Index: 673

Text #14

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.2632. Min Act: -0.1700

Data Index: 5822901 (Open Web Text)

Max Activating Token Index: 735

Text #15

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.2471. Min Act: -0.1700

Data Index: 2476369 (Open Web Text)

Max Activating Token Index: 576

Text #16

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.2665. Min Act: -0.1700

Data Index: 3812536 (Open Web Text)

Max Activating Token Index: 420

Text #17

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.2945. Min Act: -0.1700

Data Index: 2729486 (Open Web Text)

Max Activating Token Index: 808

Text #18

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.2578. Min Act: -0.1700

Data Index: 5598237 (Open Web Text)

Max Activating Token Index: 197

Text #19

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.2627. Min Act: -0.1700

Data Index: 5179088 (Open Web Text)

Max Activating Token Index: 552