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

Dataset: Open Web Text

Neuron 1065 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: 4.5190. Min Range: -4.5190

Max Act: 4.5190. Min Act: -0.1700

Data Index: 3720074 (Open Web Text)

Max Activating Token Index: 388

Text #1

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.4838. Min Act: -0.1700

Data Index: 5902902 (Open Web Text)

Max Activating Token Index: 456

Text #2

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.3850. Min Act: -0.1700

Data Index: 6787391 (Open Web Text)

Max Activating Token Index: 807

Text #3

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.3638. Min Act: -0.1700

Data Index: 3391322 (Open Web Text)

Max Activating Token Index: 465

Text #4

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.3508. Min Act: -0.1700

Data Index: 5147219 (Open Web Text)

Max Activating Token Index: 466

Text #5

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.3419. Min Act: -0.1700

Data Index: 1589851 (Open Web Text)

Max Activating Token Index: 227

Text #6

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.3008. Min Act: -0.1700

Data Index: 8329369 (Open Web Text)

Max Activating Token Index: 253

Text #7

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.3397. Min Act: -0.1700

Data Index: 1038302 (Open Web Text)

Max Activating Token Index: 528

Text #8

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.2821. Min Act: -0.1700

Data Index: 3574537 (Open Web Text)

Max Activating Token Index: 874

Text #9

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.3091. Min Act: -0.1700

Data Index: 7227266 (Open Web Text)

Max Activating Token Index: 782

Text #10

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.2755. Min Act: -0.1700

Data Index: 2419346 (Open Web Text)

Max Activating Token Index: 911

Text #11

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.2659. Min Act: -0.1700

Data Index: 661195 (Open Web Text)

Max Activating Token Index: 516

Text #12

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.2877. Min Act: -0.1700

Data Index: 1209647 (Open Web Text)

Max Activating Token Index: 69

Text #13

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.2547. Min Act: -0.1700

Data Index: 3711617 (Open Web Text)

Max Activating Token Index: 163

Text #14

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.2372. Min Act: -0.1700

Data Index: 2122344 (Open Web Text)

Max Activating Token Index: 679

Text #15

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.2512. Min Act: -0.1700

Data Index: 6007764 (Open Web Text)

Max Activating Token Index: 442

Text #16

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.2291. Min Act: -0.1700

Data Index: 2800960 (Open Web Text)

Max Activating Token Index: 847

Text #17

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.2642. Min Act: -0.1700

Data Index: 1622484 (Open Web Text)

Max Activating Token Index: 410

Text #18

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.2447. Min Act: -0.1700

Data Index: 4098209 (Open Web Text)

Max Activating Token Index: 612

Text #19

Max Range: 4.5190. Min Range: -4.5190

Max Act: 4.2675. Min Act: -0.1700

Data Index: 6306480 (Open Web Text)

Max Activating Token Index: 694