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

Dataset: Open Web Text

Neuron 1551 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: 3.4209. Min Range: -3.4209

Max Act: 3.4209. Min Act: -0.1700

Data Index: 5076512 (Open Web Text)

Max Activating Token Index: 228

Text #1

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.3439. Min Act: -0.1700

Data Index: 8403152 (Open Web Text)

Max Activating Token Index: 175

Text #2

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.3002. Min Act: -0.1700

Data Index: 8786440 (Open Web Text)

Max Activating Token Index: 44

Text #3

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.3193. Min Act: -0.1700

Data Index: 8252700 (Open Web Text)

Max Activating Token Index: 99

Text #4

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.2857. Min Act: -0.1700

Data Index: 921664 (Open Web Text)

Max Activating Token Index: 295

Text #5

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.2543. Min Act: -0.1700

Data Index: 3499711 (Open Web Text)

Max Activating Token Index: 450

Text #6

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.2259. Min Act: -0.1700

Data Index: 959040 (Open Web Text)

Max Activating Token Index: 631

Text #7

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.2549. Min Act: -0.1700

Data Index: 6330020 (Open Web Text)

Max Activating Token Index: 648

Text #8

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.2554. Min Act: -0.1700

Data Index: 7772044 (Open Web Text)

Max Activating Token Index: 705

Text #9

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.1860. Min Act: -0.1700

Data Index: 7760143 (Open Web Text)

Max Activating Token Index: 732

Text #10

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.2439. Min Act: -0.1700

Data Index: 7080842 (Open Web Text)

Max Activating Token Index: 415

Text #11

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.2014. Min Act: -0.1700

Data Index: 4842217 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.2483. Min Act: -0.1700

Data Index: 2448208 (Open Web Text)

Max Activating Token Index: 949

Text #13

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.2233. Min Act: -0.1700

Data Index: 3888825 (Open Web Text)

Max Activating Token Index: 485

Text #14

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.1482. Min Act: -0.1700

Data Index: 752625 (Open Web Text)

Max Activating Token Index: 825

Text #15

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.2163. Min Act: -0.1700

Data Index: 5774645 (Open Web Text)

Max Activating Token Index: 965

Text #16

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.1902. Min Act: -0.1700

Data Index: 8621999 (Open Web Text)

Max Activating Token Index: 808

Text #17

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.2044. Min Act: -0.1700

Data Index: 650761 (Open Web Text)

Max Activating Token Index: 25

Text #18

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.1856. Min Act: -0.1700

Data Index: 3992798 (Open Web Text)

Max Activating Token Index: 141

Text #19

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.1734. Min Act: -0.1700

Data Index: 1406484 (Open Web Text)

Max Activating Token Index: 439