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

Dataset: Open Web Text

Neuron 2717 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: 3.9488. Min Range: -3.9488

Max Act: 3.9488. Min Act: -0.1700

Data Index: 7625070 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.9035. Min Act: -0.1700

Data Index: 2900716 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.9093. Min Act: -0.1700

Data Index: 8123700 (Open Web Text)

Max Activating Token Index: 995

Text #3

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8888. Min Act: -0.1700

Data Index: 144813 (Open Web Text)

Max Activating Token Index: 379

Text #4

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8879. Min Act: -0.1700

Data Index: 153747 (Open Web Text)

Max Activating Token Index: 757

Text #5

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8221. Min Act: -0.1700

Data Index: 8297703 (Open Web Text)

Max Activating Token Index: 485

Text #6

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8560. Min Act: -0.1700

Data Index: 2584258 (Open Web Text)

Max Activating Token Index: 178

Text #7

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8607. Min Act: -0.1700

Data Index: 8523401 (Open Web Text)

Max Activating Token Index: 774

Text #8

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8386. Min Act: -0.1700

Data Index: 6486463 (Open Web Text)

Max Activating Token Index: 89

Text #9

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8064. Min Act: -0.1700

Data Index: 3470127 (Open Web Text)

Max Activating Token Index: 828

Text #10

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7861. Min Act: -0.1700

Data Index: 3798612 (Open Web Text)

Max Activating Token Index: 984

Text #11

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8076. Min Act: -0.1700

Data Index: 2694687 (Open Web Text)

Max Activating Token Index: 153

Text #12

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7997. Min Act: -0.1700

Data Index: 1331346 (Open Web Text)

Max Activating Token Index: 643

Text #13

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7703. Min Act: -0.1700

Data Index: 2820260 (Open Web Text)

Max Activating Token Index: 671

Text #14

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7764. Min Act: -0.1700

Data Index: 520443 (Open Web Text)

Max Activating Token Index: 262

Text #15

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7709. Min Act: -0.1700

Data Index: 8658620 (Open Web Text)

Max Activating Token Index: 730

Text #16

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7693. Min Act: -0.1700

Data Index: 5337472 (Open Web Text)

Max Activating Token Index: 217

Text #17

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7420. Min Act: -0.1700

Data Index: 4215406 (Open Web Text)

Max Activating Token Index: 440

Text #18

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7630. Min Act: -0.1700

Data Index: 2272940 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7808. Min Act: -0.1700

Data Index: 6476515 (Open Web Text)

Max Activating Token Index: 786