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

Dataset: Open Web Text

Neuron 179 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: 2.5833. Min Range: -2.5833

Max Act: 2.5579. Min Act: -0.1700

Data Index: 5575709 (Open Web Text)

Max Activating Token Index: 801

Text #1

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.5833. Min Act: -0.1700

Data Index: 1259692 (Open Web Text)

Max Activating Token Index: 769

Text #2

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.5646. Min Act: -0.1700

Data Index: 5925351 (Open Web Text)

Max Activating Token Index: 625

Text #3

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.5688. Min Act: -0.1700

Data Index: 7914647 (Open Web Text)

Max Activating Token Index: 880

Text #4

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.5559. Min Act: -0.1700

Data Index: 1524377 (Open Web Text)

Max Activating Token Index: 810

Text #5

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.5333. Min Act: -0.1700

Data Index: 7808513 (Open Web Text)

Max Activating Token Index: 587

Text #6

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.5173. Min Act: -0.1700

Data Index: 572799 (Open Web Text)

Max Activating Token Index: 671

Text #7

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.4939. Min Act: -0.1700

Data Index: 4851386 (Open Web Text)

Max Activating Token Index: 763

Text #8

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.5076. Min Act: -0.1700

Data Index: 1974629 (Open Web Text)

Max Activating Token Index: 619

Text #9

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.5050. Min Act: -0.1700

Data Index: 799216 (Open Web Text)

Max Activating Token Index: 630

Text #10

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.5204. Min Act: -0.1700

Data Index: 803696 (Open Web Text)

Max Activating Token Index: 470

Text #11

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.4934. Min Act: -0.1700

Data Index: 6644795 (Open Web Text)

Max Activating Token Index: 516

Text #12

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.4764. Min Act: -0.1700

Data Index: 2316539 (Open Web Text)

Max Activating Token Index: 193

Text #13

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.5132. Min Act: -0.1700

Data Index: 4138832 (Open Web Text)

Max Activating Token Index: 673

Text #14

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.5086. Min Act: -0.1700

Data Index: 2565465 (Open Web Text)

Max Activating Token Index: 854

Text #15

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.4935. Min Act: -0.1700

Data Index: 6796916 (Open Web Text)

Max Activating Token Index: 150

Text #16

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.4804. Min Act: -0.1700

Data Index: 3533124 (Open Web Text)

Max Activating Token Index: 449

Text #17

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.4636. Min Act: -0.1700

Data Index: 5292466 (Open Web Text)

Max Activating Token Index: 661

Text #18

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.4785. Min Act: -0.1700

Data Index: 6135795 (Open Web Text)

Max Activating Token Index: 868

Text #19

Max Range: 2.5833. Min Range: -2.5833

Max Act: 2.4519. Min Act: -0.1700

Data Index: 4774802 (Open Web Text)

Max Activating Token Index: 436