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

Dataset: Open Web Text

Neuron 2356 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: 5.0024. Min Range: -5.0024

Max Act: 4.9958. Min Act: -0.1700

Data Index: 6274144 (Open Web Text)

Max Activating Token Index: 132

Text #1

Max Range: 5.0024. Min Range: -5.0024

Max Act: 5.0024. Min Act: -0.1700

Data Index: 3082347 (Open Web Text)

Max Activating Token Index: 986

Text #2

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.9770. Min Act: -0.1700

Data Index: 4087671 (Open Web Text)

Max Activating Token Index: 468

Text #3

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.9071. Min Act: -0.1700

Data Index: 794775 (Open Web Text)

Max Activating Token Index: 718

Text #4

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.8959. Min Act: -0.1700

Data Index: 4212215 (Open Web Text)

Max Activating Token Index: 246

Text #5

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.8785. Min Act: -0.1700

Data Index: 3911332 (Open Web Text)

Max Activating Token Index: 41

Text #6

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.8731. Min Act: -0.1700

Data Index: 517682 (Open Web Text)

Max Activating Token Index: 395

Text #7

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.8586. Min Act: -0.1700

Data Index: 5825286 (Open Web Text)

Max Activating Token Index: 336

Text #8

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.8381. Min Act: -0.1700

Data Index: 5149652 (Open Web Text)

Max Activating Token Index: 895

Text #9

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.8112. Min Act: -0.1700

Data Index: 938560 (Open Web Text)

Max Activating Token Index: 736

Text #10

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.7994. Min Act: -0.1700

Data Index: 7060759 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.8203. Min Act: -0.1700

Data Index: 3793695 (Open Web Text)

Max Activating Token Index: 818

Text #12

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.8201. Min Act: -0.1700

Data Index: 8650607 (Open Web Text)

Max Activating Token Index: 927

Text #13

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.7650. Min Act: -0.1700

Data Index: 8210767 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.7636. Min Act: -0.1700

Data Index: 8813910 (Open Web Text)

Max Activating Token Index: 523

Text #15

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.7772. Min Act: -0.1700

Data Index: 3511126 (Open Web Text)

Max Activating Token Index: 901

Text #16

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.7663. Min Act: -0.1700

Data Index: 8172837 (Open Web Text)

Max Activating Token Index: 127

Text #17

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.7971. Min Act: -0.1700

Data Index: 2089446 (Open Web Text)

Max Activating Token Index: 370

Text #18

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.7964. Min Act: -0.1700

Data Index: 2237140 (Open Web Text)

Max Activating Token Index: 686

Text #19

Max Range: 5.0024. Min Range: -5.0024

Max Act: 4.7817. Min Act: -0.1700

Data Index: 5102080 (Open Web Text)

Max Activating Token Index: 897