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

Dataset: Open Web Text

Neuron 710 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: 5.6086. Min Range: -5.6086

Max Act: 5.6086. Min Act: -0.1700

Data Index: 5139001 (Open Web Text)

Max Activating Token Index: 634

Text #1

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.5222. Min Act: -0.1700

Data Index: 8585366 (Open Web Text)

Max Activating Token Index: 473

Text #2

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.5092. Min Act: -0.1700

Data Index: 5062544 (Open Web Text)

Max Activating Token Index: 214

Text #3

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.4558. Min Act: -0.1700

Data Index: 46022 (Open Web Text)

Max Activating Token Index: 179

Text #4

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.3729. Min Act: -0.1700

Data Index: 3407410 (Open Web Text)

Max Activating Token Index: 182

Text #5

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.2566. Min Act: -0.1700

Data Index: 4245099 (Open Web Text)

Max Activating Token Index: 951

Text #6

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.2464. Min Act: -0.1700

Data Index: 2499021 (Open Web Text)

Max Activating Token Index: 741

Text #7

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.2595. Min Act: -0.1700

Data Index: 2870977 (Open Web Text)

Max Activating Token Index: 1005

Text #8

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.2428. Min Act: -0.1700

Data Index: 4297730 (Open Web Text)

Max Activating Token Index: 472

Text #9

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.2345. Min Act: -0.1700

Data Index: 2772197 (Open Web Text)

Max Activating Token Index: 682

Text #10

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.2043. Min Act: -0.1700

Data Index: 6644111 (Open Web Text)

Max Activating Token Index: 357

Text #11

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.2232. Min Act: -0.1700

Data Index: 953471 (Open Web Text)

Max Activating Token Index: 637

Text #12

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.1733. Min Act: -0.1700

Data Index: 5956120 (Open Web Text)

Max Activating Token Index: 305

Text #13

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.2028. Min Act: -0.1700

Data Index: 2829852 (Open Web Text)

Max Activating Token Index: 115

Text #14

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.1608. Min Act: -0.1700

Data Index: 5015698 (Open Web Text)

Max Activating Token Index: 397

Text #15

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.1700. Min Act: -0.1700

Data Index: 1008654 (Open Web Text)

Max Activating Token Index: 683

Text #16

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.1352. Min Act: -0.1700

Data Index: 6684745 (Open Web Text)

Max Activating Token Index: 813

Text #17

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.1851. Min Act: -0.1700

Data Index: 5073808 (Open Web Text)

Max Activating Token Index: 308

Text #18

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.1418. Min Act: -0.1700

Data Index: 5578484 (Open Web Text)

Max Activating Token Index: 244

Text #19

Max Range: 5.6086. Min Range: -5.6086

Max Act: 5.1459. Min Act: -0.1700

Data Index: 7319177 (Open Web Text)

Max Activating Token Index: 496