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

Dataset: Open Web Text

Neuron 35 in Layer 3

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: 3.3856. Min Range: -3.3856

Max Act: 3.3856. Min Act: -0.1700

Data Index: 6763420 (Open Web Text)

Max Activating Token Index: 370

Text #1

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2943. Min Act: -0.1700

Data Index: 3194012 (Open Web Text)

Max Activating Token Index: 490

Text #2

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.3361. Min Act: -0.1700

Data Index: 4140407 (Open Web Text)

Max Activating Token Index: 149

Text #3

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2924. Min Act: -0.1700

Data Index: 1697198 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2747. Min Act: -0.1700

Data Index: 2304389 (Open Web Text)

Max Activating Token Index: 826

Text #5

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2790. Min Act: -0.1700

Data Index: 2653589 (Open Web Text)

Max Activating Token Index: 732

Text #6

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2296. Min Act: -0.1700

Data Index: 3750451 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1727. Min Act: -0.1700

Data Index: 7388616 (Open Web Text)

Max Activating Token Index: 214

Text #8

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1707. Min Act: -0.1700

Data Index: 5756850 (Open Web Text)

Max Activating Token Index: 565

Text #9

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2057. Min Act: -0.1700

Data Index: 2320376 (Open Web Text)

Max Activating Token Index: 324

Text #10

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1709. Min Act: -0.1700

Data Index: 4848085 (Open Web Text)

Max Activating Token Index: 375

Text #11

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1466. Min Act: -0.1700

Data Index: 66868 (Open Web Text)

Max Activating Token Index: 943

Text #12

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1755. Min Act: -0.1700

Data Index: 4676768 (Open Web Text)

Max Activating Token Index: 522

Text #13

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1391. Min Act: -0.1700

Data Index: 6274084 (Open Web Text)

Max Activating Token Index: 342

Text #14

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1523. Min Act: -0.1700

Data Index: 4640934 (Open Web Text)

Max Activating Token Index: 118

Text #15

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1159. Min Act: -0.1700

Data Index: 3302276 (Open Web Text)

Max Activating Token Index: 589

Text #16

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1230. Min Act: -0.1700

Data Index: 3023071 (Open Web Text)

Max Activating Token Index: 388

Text #17

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1237. Min Act: -0.1700

Data Index: 7038866 (Open Web Text)

Max Activating Token Index: 130

Text #18

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1246. Min Act: -0.1700

Data Index: 7535898 (Open Web Text)

Max Activating Token Index: 92

Text #19

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.0986. Min Act: -0.1700

Data Index: 1756090 (Open Web Text)

Max Activating Token Index: 776