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

Dataset: Open Web Text

Neuron 2010 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: 4.5069. Min Range: -4.5069

Max Act: 4.5069. Min Act: -0.1700

Data Index: 2663191 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.5019. Min Act: -0.1700

Data Index: 343527 (Open Web Text)

Max Activating Token Index: 580

Text #2

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.4108. Min Act: -0.1700

Data Index: 3342190 (Open Web Text)

Max Activating Token Index: 668

Text #3

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.4217. Min Act: -0.1700

Data Index: 7823498 (Open Web Text)

Max Activating Token Index: 169

Text #4

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.3531. Min Act: -0.1700

Data Index: 2868559 (Open Web Text)

Max Activating Token Index: 267

Text #5

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2671. Min Act: -0.1700

Data Index: 1781033 (Open Web Text)

Max Activating Token Index: 619

Text #6

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2966. Min Act: -0.1700

Data Index: 5187992 (Open Web Text)

Max Activating Token Index: 340

Text #7

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2901. Min Act: -0.1700

Data Index: 1049936 (Open Web Text)

Max Activating Token Index: 85

Text #8

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2825. Min Act: -0.1700

Data Index: 3659437 (Open Web Text)

Max Activating Token Index: 326

Text #9

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2813. Min Act: -0.1700

Data Index: 8103088 (Open Web Text)

Max Activating Token Index: 329

Text #10

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2883. Min Act: -0.1700

Data Index: 6455280 (Open Web Text)

Max Activating Token Index: 644

Text #11

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2874. Min Act: -0.1700

Data Index: 3458566 (Open Web Text)

Max Activating Token Index: 862

Text #12

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.3002. Min Act: -0.1700

Data Index: 5750833 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2639. Min Act: -0.1700

Data Index: 8097860 (Open Web Text)

Max Activating Token Index: 167

Text #14

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2582. Min Act: -0.1700

Data Index: 3402056 (Open Web Text)

Max Activating Token Index: 761

Text #15

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2524. Min Act: -0.1700

Data Index: 8178990 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2439. Min Act: -0.1700

Data Index: 7539455 (Open Web Text)

Max Activating Token Index: 819

Text #17

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2195. Min Act: -0.1700

Data Index: 8343367 (Open Web Text)

Max Activating Token Index: 600

Text #18

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2393. Min Act: -0.1700

Data Index: 59003 (Open Web Text)

Max Activating Token Index: 46

Text #19

Max Range: 4.5069. Min Range: -4.5069

Max Act: 4.2446. Min Act: -0.1700

Data Index: 1283035 (Open Web Text)

Max Activating Token Index: 766