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

Dataset: Open Web Text

Neuron 192 in Layer 5

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: 3.4570. Min Range: -3.4570

Max Act: 3.4570. Min Act: -0.1700

Data Index: 6530054 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.3786. Min Act: -0.1700

Data Index: 1051723 (Open Web Text)

Max Activating Token Index: 704

Text #2

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.3238. Min Act: -0.1700

Data Index: 6929167 (Open Web Text)

Max Activating Token Index: 949

Text #3

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.3201. Min Act: -0.1700

Data Index: 7956937 (Open Web Text)

Max Activating Token Index: 571

Text #4

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.3197. Min Act: -0.1700

Data Index: 2601569 (Open Web Text)

Max Activating Token Index: 415

Text #5

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.3171. Min Act: -0.1700

Data Index: 5184656 (Open Web Text)

Max Activating Token Index: 371

Text #6

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2907. Min Act: -0.1700

Data Index: 6050299 (Open Web Text)

Max Activating Token Index: 126

Text #7

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.3070. Min Act: -0.1700

Data Index: 7594376 (Open Web Text)

Max Activating Token Index: 60

Text #8

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.3024. Min Act: -0.1700

Data Index: 1089903 (Open Web Text)

Max Activating Token Index: 763

Text #9

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2625. Min Act: -0.1700

Data Index: 5289157 (Open Web Text)

Max Activating Token Index: 270

Text #10

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2793. Min Act: -0.1700

Data Index: 5753339 (Open Web Text)

Max Activating Token Index: 444

Text #11

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2724. Min Act: -0.1700

Data Index: 6531428 (Open Web Text)

Max Activating Token Index: 781

Text #12

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2660. Min Act: -0.1700

Data Index: 7442388 (Open Web Text)

Max Activating Token Index: 946

Text #13

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2580. Min Act: -0.1700

Data Index: 4794783 (Open Web Text)

Max Activating Token Index: 897

Text #14

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2681. Min Act: -0.1700

Data Index: 2570440 (Open Web Text)

Max Activating Token Index: 608

Text #15

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2488. Min Act: -0.1700

Data Index: 3929051 (Open Web Text)

Max Activating Token Index: 537

Text #16

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2778. Min Act: -0.1700

Data Index: 6138826 (Open Web Text)

Max Activating Token Index: 411

Text #17

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2445. Min Act: -0.1700

Data Index: 5648940 (Open Web Text)

Max Activating Token Index: 274

Text #18

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2375. Min Act: -0.1700

Data Index: 6056443 (Open Web Text)

Max Activating Token Index: 709

Text #19

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2368. Min Act: -0.1700

Data Index: 8148472 (Open Web Text)

Max Activating Token Index: 446