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

Dataset: Open Web Text

Neuron 2776 in Layer 6

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: 4.5929. Min Range: -4.5929

Max Act: 4.5929. Min Act: -0.1700

Data Index: 40923 (Open Web Text)

Max Activating Token Index: 671

Text #1

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.4083. Min Act: -0.1700

Data Index: 5991763 (Open Web Text)

Max Activating Token Index: 830

Text #2

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.3698. Min Act: -0.1700

Data Index: 3678082 (Open Web Text)

Max Activating Token Index: 370

Text #3

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.3444. Min Act: -0.1700

Data Index: 4720991 (Open Web Text)

Max Activating Token Index: 848

Text #4

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.2790. Min Act: -0.1700

Data Index: 2425114 (Open Web Text)

Max Activating Token Index: 185

Text #5

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.2642. Min Act: -0.1700

Data Index: 3177991 (Open Web Text)

Max Activating Token Index: 358

Text #6

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.2636. Min Act: -0.1700

Data Index: 3106549 (Open Web Text)

Max Activating Token Index: 597

Text #7

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.2880. Min Act: -0.1700

Data Index: 1386435 (Open Web Text)

Max Activating Token Index: 234

Text #8

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.2466. Min Act: -0.1700

Data Index: 1629528 (Open Web Text)

Max Activating Token Index: 772

Text #9

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.2740. Min Act: -0.1700

Data Index: 3586079 (Open Web Text)

Max Activating Token Index: 778

Text #10

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.2345. Min Act: -0.1700

Data Index: 6751354 (Open Web Text)

Max Activating Token Index: 215

Text #11

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.2163. Min Act: -0.1700

Data Index: 8493063 (Open Web Text)

Max Activating Token Index: 695

Text #12

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.2079. Min Act: -0.1700

Data Index: 6601290 (Open Web Text)

Max Activating Token Index: 754

Text #13

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.2338. Min Act: -0.1700

Data Index: 1655197 (Open Web Text)

Max Activating Token Index: 663

Text #14

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.1380. Min Act: -0.1700

Data Index: 8379064 (Open Web Text)

Max Activating Token Index: 1016

Text #15

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.1779. Min Act: -0.1700

Data Index: 4368626 (Open Web Text)

Max Activating Token Index: 766

Text #16

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.1693. Min Act: -0.1700

Data Index: 2733818 (Open Web Text)

Max Activating Token Index: 645

Text #17

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.2384. Min Act: -0.1700

Data Index: 3438065 (Open Web Text)

Max Activating Token Index: 867

Text #18

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.1872. Min Act: -0.1700

Data Index: 2807295 (Open Web Text)

Max Activating Token Index: 398

Text #19

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.1696. Min Act: -0.1700

Data Index: 2161617 (Open Web Text)

Max Activating Token Index: 497